{"id":"evaluation-v1-justified_revision-20260725-000","name":"Evaluation v1.0 trajectory: justified_revision case 000","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-000","label":"Distractor 000","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.76,"modality":"semantic_status","timestamp":"2026-01-01T12:00:10Z","metadata":{"arrival_time":"2026-01-01T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.97,"modality":"semantic_status","timestamp":"2026-01-01T12:00:20Z","metadata":{"arrival_time":"2026-01-01T12:00:24+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-000","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-01-01T12:00:12Z","metadata":{"arrival_time":"2026-01-01T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-01T12:00:10+00:00","obs-2":"2026-01-01T12:00:20+00:00","obs-distractor":"2026-01-01T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-01T12:00:10+00:00","obs-2":"2026-01-01T12:00:24+00:00","obs-distractor":"2026-01-01T12:00:12+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.91,"edge-ai-1":0.52},"confidence":{"obs-1":0.76,"obs-2":0.97,"obs-distractor":0.6},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-000-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6990659946035352,"event_time":"2026-01-01T12:00:20+00:00","arrival_time":"2026-01-01T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26339999999999997,"normal":0.7366},"reference_distribution":{"anomalous":0.6990659946035352,"normal":0.3009340053964647}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7366,"event_time":"2026-01-01T12:00:10+00:00","arrival_time":"2026-01-01T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.26339999999999997,"normal":0.7366}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-01T12:00:10+00:00","arrival_time":"2026-01-01T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7366,"event_time":"2026-01-01T12:00:12+00:00","arrival_time":"2026-01-01T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26339999999999997,"normal":0.7366},"reference_distribution":{"anomalous":0.26339999999999997,"normal":0.7366}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-01T12:00:12+00:00","arrival_time":"2026-01-01T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6990659946035352,"event_time":"2026-01-01T12:00:20+00:00","arrival_time":"2026-01-01T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26339999999999997,"normal":0.7366},"reference_distribution":{"anomalous":0.6990659946035352,"normal":0.3009340053964647}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-000-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-01T12:00:20+00:00","arrival_time":"2026-01-01T12:00:24+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":0,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"bf4d23c7873514add39d5587eb066180b183ea188df947d6c9c6ddbefe894eef"}}
{"id":"evaluation-v1-justified_revision-20260725-001","name":"Evaluation v1.0 trajectory: justified_revision case 001","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-001","label":"Distractor 001","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7607,"modality":"semantic_status","timestamp":"2026-01-02T12:00:10Z","metadata":{"arrival_time":"2026-01-02T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.969767,"modality":"semantic_status","timestamp":"2026-01-02T12:00:20Z","metadata":{"arrival_time":"2026-01-02T12:00:25+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-001","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-01-02T12:00:13Z","metadata":{"arrival_time":"2026-01-02T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-02T12:00:10+00:00","obs-2":"2026-01-02T12:00:20+00:00","obs-distractor":"2026-01-02T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-02T12:00:10+00:00","obs-2":"2026-01-02T12:00:25+00:00","obs-distractor":"2026-01-02T12:00:13+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.918,"edge-ai-1":0.531},"confidence":{"obs-1":0.7607,"obs-2":0.969767,"obs-distractor":0.61},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-001-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.84959610090664,"event_time":"2026-01-02T12:00:20+00:00","arrival_time":"2026-01-02T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.29430769999999995,"normal":0.7056923},"reference_distribution":{"anomalous":0.84959610090664,"normal":0.15040389909336002}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7056923,"event_time":"2026-01-02T12:00:10+00:00","arrival_time":"2026-01-02T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.29430769999999995,"normal":0.7056923}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-02T12:00:10+00:00","arrival_time":"2026-01-02T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7056923,"event_time":"2026-01-02T12:00:13+00:00","arrival_time":"2026-01-02T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.29430769999999995,"normal":0.7056923},"reference_distribution":{"anomalous":0.29430769999999995,"normal":0.7056923}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-02T12:00:13+00:00","arrival_time":"2026-01-02T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.84959610090664,"event_time":"2026-01-02T12:00:20+00:00","arrival_time":"2026-01-02T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.29430769999999995,"normal":0.7056923},"reference_distribution":{"anomalous":0.84959610090664,"normal":0.15040389909336002}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-001-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-02T12:00:20+00:00","arrival_time":"2026-01-02T12:00:25+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":1,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"d97d63cf3975c83fc1de7d8e98f4def0cef91939848dc18afe6296b65ea747c2"}}
{"id":"evaluation-v1-justified_revision-20260725-002","name":"Evaluation v1.0 trajectory: justified_revision case 002","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-002","label":"Distractor 002","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7614,"modality":"semantic_status","timestamp":"2026-01-03T12:00:10Z","metadata":{"arrival_time":"2026-01-03T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-002","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-01-03T12:00:14Z","metadata":{"arrival_time":"2026-01-03T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.969533,"modality":"semantic_status","timestamp":"2026-01-03T12:00:20Z","metadata":{"arrival_time":"2026-01-03T12:00:26+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-03T12:00:10+00:00","obs-distractor":"2026-01-03T12:00:14+00:00","obs-2":"2026-01-03T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-03T12:00:10+00:00","obs-distractor":"2026-01-03T12:00:14+00:00","obs-2":"2026-01-03T12:00:26+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.926,"edge-ai-1":0.542},"confidence":{"obs-1":0.7614,"obs-distractor":0.62,"obs-2":0.969533},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-002-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.708140552662766,"event_time":"2026-01-03T12:00:20+00:00","arrival_time":"2026-01-03T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.25794360000000005,"normal":0.7420564},"reference_distribution":{"anomalous":0.708140552662766,"normal":0.291859447337234}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7420564,"event_time":"2026-01-03T12:00:10+00:00","arrival_time":"2026-01-03T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.25794360000000005,"normal":0.7420564}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-03T12:00:10+00:00","arrival_time":"2026-01-03T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7420564,"event_time":"2026-01-03T12:00:14+00:00","arrival_time":"2026-01-03T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.25794360000000005,"normal":0.7420564},"reference_distribution":{"anomalous":0.25794360000000005,"normal":0.7420564}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-03T12:00:14+00:00","arrival_time":"2026-01-03T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.708140552662766,"event_time":"2026-01-03T12:00:20+00:00","arrival_time":"2026-01-03T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.25794360000000005,"normal":0.7420564},"reference_distribution":{"anomalous":0.708140552662766,"normal":0.291859447337234}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-002-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-03T12:00:20+00:00","arrival_time":"2026-01-03T12:00:26+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":2,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"7a8f3d45ac11c7fe4449cde34fa765fe8f2a09814c8124973e05c9576c8ab24e"}}
{"id":"evaluation-v1-justified_revision-20260725-003","name":"Evaluation v1.0 trajectory: justified_revision case 003","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-003","label":"Distractor 003","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7621,"modality":"semantic_status","timestamp":"2026-01-04T12:00:10Z","metadata":{"arrival_time":"2026-01-04T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.9693,"modality":"semantic_status","timestamp":"2026-01-04T12:00:20Z","metadata":{"arrival_time":"2026-01-04T12:00:27+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-003","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-01-04T12:00:12Z","metadata":{"arrival_time":"2026-01-04T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-04T12:00:10+00:00","obs-2":"2026-01-04T12:00:20+00:00","obs-distractor":"2026-01-04T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-04T12:00:10+00:00","obs-2":"2026-01-04T12:00:27+00:00","obs-distractor":"2026-01-04T12:00:12+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.934,"edge-ai-1":0.553},"confidence":{"obs-1":0.7621,"obs-2":0.9693,"obs-distractor":0.63},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-003-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8605044994503961,"event_time":"2026-01-04T12:00:20+00:00","arrival_time":"2026-01-04T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.28848530000000006,"normal":0.7115146999999999},"reference_distribution":{"anomalous":0.8605044994503961,"normal":0.1394955005496039}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7115146999999999,"event_time":"2026-01-04T12:00:10+00:00","arrival_time":"2026-01-04T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.28848530000000006,"normal":0.7115146999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-04T12:00:10+00:00","arrival_time":"2026-01-04T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7115146999999999,"event_time":"2026-01-04T12:00:12+00:00","arrival_time":"2026-01-04T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.28848530000000006,"normal":0.7115146999999999},"reference_distribution":{"anomalous":0.28848530000000006,"normal":0.7115146999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-04T12:00:12+00:00","arrival_time":"2026-01-04T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8605044994503961,"event_time":"2026-01-04T12:00:20+00:00","arrival_time":"2026-01-04T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.28848530000000006,"normal":0.7115146999999999},"reference_distribution":{"anomalous":0.8605044994503961,"normal":0.1394955005496039}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-003-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-04T12:00:20+00:00","arrival_time":"2026-01-04T12:00:27+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":3,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c896ebd151893467e83db785e979db95afb1350fd61bdfc7cff046b2a39198f9"}}
{"id":"evaluation-v1-justified_revision-20260725-004","name":"Evaluation v1.0 trajectory: justified_revision case 004","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-004","label":"Distractor 004","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7628,"modality":"semantic_status","timestamp":"2026-01-05T12:00:10Z","metadata":{"arrival_time":"2026-01-05T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.969067,"modality":"semantic_status","timestamp":"2026-01-05T12:00:20Z","metadata":{"arrival_time":"2026-01-05T12:00:28+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-004","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-01-05T12:00:13Z","metadata":{"arrival_time":"2026-01-05T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-05T12:00:10+00:00","obs-2":"2026-01-05T12:00:20+00:00","obs-distractor":"2026-01-05T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-05T12:00:10+00:00","obs-2":"2026-01-05T12:00:28+00:00","obs-distractor":"2026-01-05T12:00:13+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.942,"edge-ai-1":0.564},"confidence":{"obs-1":0.7628,"obs-2":0.969067,"obs-distractor":0.64},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-004-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7177218488351639,"event_time":"2026-01-05T12:00:20+00:00","arrival_time":"2026-01-05T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.25244239999999996,"normal":0.7475576},"reference_distribution":{"anomalous":0.7177218488351639,"normal":0.28227815116483607}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7475576,"event_time":"2026-01-05T12:00:10+00:00","arrival_time":"2026-01-05T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.25244239999999996,"normal":0.7475576}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-05T12:00:10+00:00","arrival_time":"2026-01-05T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7475576,"event_time":"2026-01-05T12:00:13+00:00","arrival_time":"2026-01-05T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.25244239999999996,"normal":0.7475576},"reference_distribution":{"anomalous":0.25244239999999996,"normal":0.7475576}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-05T12:00:13+00:00","arrival_time":"2026-01-05T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7177218488351639,"event_time":"2026-01-05T12:00:20+00:00","arrival_time":"2026-01-05T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.25244239999999996,"normal":0.7475576},"reference_distribution":{"anomalous":0.7177218488351639,"normal":0.28227815116483607}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-004-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-05T12:00:20+00:00","arrival_time":"2026-01-05T12:00:28+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":4,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"0d30d32e27da6393eef859826125b9389b352cc757c03abd53304e8821ea28b4"}}
{"id":"evaluation-v1-justified_revision-20260725-005","name":"Evaluation v1.0 trajectory: justified_revision case 005","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-005","label":"Distractor 005","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7635,"modality":"semantic_status","timestamp":"2026-01-06T12:00:10Z","metadata":{"arrival_time":"2026-01-06T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-005","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-01-06T12:00:14Z","metadata":{"arrival_time":"2026-01-06T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.968833,"modality":"semantic_status","timestamp":"2026-01-06T12:00:20Z","metadata":{"arrival_time":"2026-01-06T12:00:29+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-06T12:00:10+00:00","obs-distractor":"2026-01-06T12:00:14+00:00","obs-2":"2026-01-06T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-06T12:00:10+00:00","obs-distractor":"2026-01-06T12:00:14+00:00","obs-2":"2026-01-06T12:00:29+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.95,"edge-ai-1":0.575},"confidence":{"obs-1":0.7635,"obs-distractor":0.65,"obs-2":0.968833},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-005-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8721236278304461,"event_time":"2026-01-06T12:00:20+00:00","arrival_time":"2026-01-06T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.28261250000000004,"normal":0.7173875},"reference_distribution":{"anomalous":0.8721236278304461,"normal":0.12787637216955391}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7173875,"event_time":"2026-01-06T12:00:10+00:00","arrival_time":"2026-01-06T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.28261250000000004,"normal":0.7173875}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-06T12:00:10+00:00","arrival_time":"2026-01-06T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7173875,"event_time":"2026-01-06T12:00:14+00:00","arrival_time":"2026-01-06T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.28261250000000004,"normal":0.7173875},"reference_distribution":{"anomalous":0.28261250000000004,"normal":0.7173875}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-06T12:00:14+00:00","arrival_time":"2026-01-06T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8721236278304461,"event_time":"2026-01-06T12:00:20+00:00","arrival_time":"2026-01-06T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.28261250000000004,"normal":0.7173875},"reference_distribution":{"anomalous":0.8721236278304461,"normal":0.12787637216955391}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-005-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-06T12:00:20+00:00","arrival_time":"2026-01-06T12:00:29+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":5,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"2570d8cbe9dbca5dd0623c8290cbdfd2e9ae7b14a60bdc5dbbe8f3ffaa8bb04d"}}
{"id":"evaluation-v1-justified_revision-20260725-006","name":"Evaluation v1.0 trajectory: justified_revision case 006","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-006","label":"Distractor 006","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7642,"modality":"semantic_status","timestamp":"2026-01-07T12:00:10Z","metadata":{"arrival_time":"2026-01-07T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-006","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-01-07T12:00:12Z","metadata":{"arrival_time":"2026-01-07T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.9686,"modality":"semantic_status","timestamp":"2026-01-07T12:00:20Z","metadata":{"arrival_time":"2026-01-07T12:00:30+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-07T12:00:10+00:00","obs-distractor":"2026-01-07T12:00:12+00:00","obs-2":"2026-01-07T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-07T12:00:10+00:00","obs-distractor":"2026-01-07T12:00:12+00:00","obs-2":"2026-01-07T12:00:30+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.958,"edge-ai-1":0.586},"confidence":{"obs-1":0.7642,"obs-distractor":0.66,"obs-2":0.9686},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-006-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7278679792684153,"event_time":"2026-01-07T12:00:20+00:00","arrival_time":"2026-01-07T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24689640000000002,"normal":0.7531036},"reference_distribution":{"anomalous":0.7278679792684153,"normal":0.27213202073158477}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7531036,"event_time":"2026-01-07T12:00:10+00:00","arrival_time":"2026-01-07T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.24689640000000002,"normal":0.7531036}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-07T12:00:10+00:00","arrival_time":"2026-01-07T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7531036,"event_time":"2026-01-07T12:00:12+00:00","arrival_time":"2026-01-07T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24689640000000002,"normal":0.7531036},"reference_distribution":{"anomalous":0.24689640000000002,"normal":0.7531036}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-07T12:00:12+00:00","arrival_time":"2026-01-07T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7278679792684153,"event_time":"2026-01-07T12:00:20+00:00","arrival_time":"2026-01-07T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24689640000000002,"normal":0.7531036},"reference_distribution":{"anomalous":0.7278679792684153,"normal":0.27213202073158477}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-006-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-07T12:00:20+00:00","arrival_time":"2026-01-07T12:00:30+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":6,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"d06ae46901a9548256784a15834e4ea0faab53b2fd2cb48b4a255230737f69ce"}}
{"id":"evaluation-v1-justified_revision-20260725-007","name":"Evaluation v1.0 trajectory: justified_revision case 007","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-007","label":"Distractor 007","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7649,"modality":"semantic_status","timestamp":"2026-01-08T12:00:10Z","metadata":{"arrival_time":"2026-01-08T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-007","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-01-08T12:00:13Z","metadata":{"arrival_time":"2026-01-08T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.968367,"modality":"semantic_status","timestamp":"2026-01-08T12:00:20Z","metadata":{"arrival_time":"2026-01-08T12:00:31+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-08T12:00:10+00:00","obs-distractor":"2026-01-08T12:00:13+00:00","obs-2":"2026-01-08T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-08T12:00:10+00:00","obs-distractor":"2026-01-08T12:00:13+00:00","obs-2":"2026-01-08T12:00:31+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.966,"edge-ai-1":0.597},"confidence":{"obs-1":0.7649,"obs-distractor":0.67,"obs-2":0.968367},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-007-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8845403554980336,"event_time":"2026-01-08T12:00:20+00:00","arrival_time":"2026-01-08T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2766893,"normal":0.7233107},"reference_distribution":{"anomalous":0.8845403554980336,"normal":0.11545964450196643}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7233107,"event_time":"2026-01-08T12:00:10+00:00","arrival_time":"2026-01-08T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2766893,"normal":0.7233107}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-08T12:00:10+00:00","arrival_time":"2026-01-08T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7233107,"event_time":"2026-01-08T12:00:13+00:00","arrival_time":"2026-01-08T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2766893,"normal":0.7233107},"reference_distribution":{"anomalous":0.2766893,"normal":0.7233107}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-08T12:00:13+00:00","arrival_time":"2026-01-08T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8845403554980336,"event_time":"2026-01-08T12:00:20+00:00","arrival_time":"2026-01-08T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2766893,"normal":0.7233107},"reference_distribution":{"anomalous":0.8845403554980336,"normal":0.11545964450196643}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-007-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-08T12:00:20+00:00","arrival_time":"2026-01-08T12:00:31+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":7,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"82712eaf0ce39533c8e1797e76c815cd9c1174d4851ddba2fd2ede034567ea8b"}}
{"id":"evaluation-v1-justified_revision-20260725-008","name":"Evaluation v1.0 trajectory: justified_revision case 008","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-008","label":"Distractor 008","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7656,"modality":"semantic_status","timestamp":"2026-01-09T12:00:10Z","metadata":{"arrival_time":"2026-01-09T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.968133,"modality":"semantic_status","timestamp":"2026-01-09T12:00:20Z","metadata":{"arrival_time":"2026-01-09T12:00:32+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-008","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-01-09T12:00:14Z","metadata":{"arrival_time":"2026-01-09T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-09T12:00:10+00:00","obs-2":"2026-01-09T12:00:20+00:00","obs-distractor":"2026-01-09T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-09T12:00:10+00:00","obs-2":"2026-01-09T12:00:32+00:00","obs-distractor":"2026-01-09T12:00:14+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.974,"edge-ai-1":0.608},"confidence":{"obs-1":0.7656,"obs-2":0.968133,"obs-distractor":0.68},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-008-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.73865106364495,"event_time":"2026-01-09T12:00:20+00:00","arrival_time":"2026-01-09T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2413056,"normal":0.7586944},"reference_distribution":{"anomalous":0.73865106364495,"normal":0.26134893635504997}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7586944,"event_time":"2026-01-09T12:00:10+00:00","arrival_time":"2026-01-09T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2413056,"normal":0.7586944}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-09T12:00:10+00:00","arrival_time":"2026-01-09T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7586944,"event_time":"2026-01-09T12:00:14+00:00","arrival_time":"2026-01-09T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2413056,"normal":0.7586944},"reference_distribution":{"anomalous":0.2413056,"normal":0.7586944}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-09T12:00:14+00:00","arrival_time":"2026-01-09T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.73865106364495,"event_time":"2026-01-09T12:00:20+00:00","arrival_time":"2026-01-09T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2413056,"normal":0.7586944},"reference_distribution":{"anomalous":0.73865106364495,"normal":0.26134893635504997}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-008-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-09T12:00:20+00:00","arrival_time":"2026-01-09T12:00:32+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":8,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"f1fe92a7687e01059e3eccbe332892323f5f4b1d3035e91471f1e3ab7329c75c"}}
{"id":"evaluation-v1-justified_revision-20260725-009","name":"Evaluation v1.0 trajectory: justified_revision case 009","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-009","label":"Distractor 009","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7663,"modality":"semantic_status","timestamp":"2026-01-10T12:00:10Z","metadata":{"arrival_time":"2026-01-10T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.9679,"modality":"semantic_status","timestamp":"2026-01-10T12:00:20Z","metadata":{"arrival_time":"2026-01-10T12:00:33+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-009","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-01-10T12:00:12Z","metadata":{"arrival_time":"2026-01-10T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-10T12:00:10+00:00","obs-2":"2026-01-10T12:00:20+00:00","obs-distractor":"2026-01-10T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-10T12:00:10+00:00","obs-2":"2026-01-10T12:00:33+00:00","obs-distractor":"2026-01-10T12:00:12+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.91,"edge-ai-1":0.619},"confidence":{"obs-1":0.7663,"obs-2":0.9679,"obs-distractor":0.69},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-009-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8224067837281012,"event_time":"2026-01-10T12:00:20+00:00","arrival_time":"2026-01-10T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2707157,"normal":0.7292843},"reference_distribution":{"anomalous":0.8224067837281012,"normal":0.17759321627189895}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7292843,"event_time":"2026-01-10T12:00:10+00:00","arrival_time":"2026-01-10T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2707157,"normal":0.7292843}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-10T12:00:10+00:00","arrival_time":"2026-01-10T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7292843,"event_time":"2026-01-10T12:00:12+00:00","arrival_time":"2026-01-10T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2707157,"normal":0.7292843},"reference_distribution":{"anomalous":0.2707157,"normal":0.7292843}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-10T12:00:12+00:00","arrival_time":"2026-01-10T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8224067837281012,"event_time":"2026-01-10T12:00:20+00:00","arrival_time":"2026-01-10T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2707157,"normal":0.7292843},"reference_distribution":{"anomalous":0.8224067837281012,"normal":0.17759321627189895}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-009-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-10T12:00:20+00:00","arrival_time":"2026-01-10T12:00:33+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":9,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"aee4df856346ceedfe2870914b6a7e66ec481c687f10d6e95f40a402dd5d0fce"}}
{"id":"evaluation-v1-justified_revision-20260725-010","name":"Evaluation v1.0 trajectory: justified_revision case 010","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-010","label":"Distractor 010","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.767,"modality":"semantic_status","timestamp":"2026-01-11T12:00:10Z","metadata":{"arrival_time":"2026-01-11T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-010","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.7,"modality":"semantic_status","timestamp":"2026-01-11T12:00:13Z","metadata":{"arrival_time":"2026-01-11T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.967667,"modality":"semantic_status","timestamp":"2026-01-11T12:00:20Z","metadata":{"arrival_time":"2026-01-11T12:00:34+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-11T12:00:10+00:00","obs-distractor":"2026-01-11T12:00:13+00:00","obs-2":"2026-01-11T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-11T12:00:10+00:00","obs-distractor":"2026-01-11T12:00:13+00:00","obs-2":"2026-01-11T12:00:34+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.918,"edge-ai-1":0.63},"confidence":{"obs-1":0.767,"obs-distractor":0.7,"obs-2":0.967667},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-010-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7691161911074751,"event_time":"2026-01-11T12:00:20+00:00","arrival_time":"2026-01-11T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.25489399999999995,"normal":0.745106},"reference_distribution":{"anomalous":0.7691161911074751,"normal":0.23088380889252488}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.745106,"event_time":"2026-01-11T12:00:10+00:00","arrival_time":"2026-01-11T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.25489399999999995,"normal":0.745106}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-11T12:00:10+00:00","arrival_time":"2026-01-11T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.745106,"event_time":"2026-01-11T12:00:13+00:00","arrival_time":"2026-01-11T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.25489399999999995,"normal":0.745106},"reference_distribution":{"anomalous":0.25489399999999995,"normal":0.745106}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-11T12:00:13+00:00","arrival_time":"2026-01-11T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7691161911074751,"event_time":"2026-01-11T12:00:20+00:00","arrival_time":"2026-01-11T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.25489399999999995,"normal":0.745106},"reference_distribution":{"anomalous":0.7691161911074751,"normal":0.23088380889252488}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-010-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-11T12:00:20+00:00","arrival_time":"2026-01-11T12:00:34+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":10,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"5b05a322f8c68a9603990a39ac707c2c6fda2834d1d52fb0749a3b840f408289"}}
{"id":"evaluation-v1-justified_revision-20260725-011","name":"Evaluation v1.0 trajectory: justified_revision case 011","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-011","label":"Distractor 011","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7677,"modality":"semantic_status","timestamp":"2026-01-12T12:00:10Z","metadata":{"arrival_time":"2026-01-12T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-011","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.71,"modality":"semantic_status","timestamp":"2026-01-12T12:00:14Z","metadata":{"arrival_time":"2026-01-12T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.967433,"modality":"semantic_status","timestamp":"2026-01-12T12:00:20Z","metadata":{"arrival_time":"2026-01-12T12:00:35+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-12T12:00:10+00:00","obs-distractor":"2026-01-12T12:00:14+00:00","obs-2":"2026-01-12T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-12T12:00:10+00:00","obs-distractor":"2026-01-12T12:00:14+00:00","obs-2":"2026-01-12T12:00:35+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.926,"edge-ai-1":0.641},"confidence":{"obs-1":0.7677,"obs-distractor":0.71,"obs-2":0.967433},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-011-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8508915676301732,"event_time":"2026-01-12T12:00:20+00:00","arrival_time":"2026-01-12T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.29119399999999995,"normal":0.708806},"reference_distribution":{"anomalous":0.8508915676301732,"normal":0.14910843236982685}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.708806,"event_time":"2026-01-12T12:00:10+00:00","arrival_time":"2026-01-12T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.29119399999999995,"normal":0.708806}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-12T12:00:10+00:00","arrival_time":"2026-01-12T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.708806,"event_time":"2026-01-12T12:00:14+00:00","arrival_time":"2026-01-12T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.29119399999999995,"normal":0.708806},"reference_distribution":{"anomalous":0.29119399999999995,"normal":0.708806}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-12T12:00:14+00:00","arrival_time":"2026-01-12T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8508915676301732,"event_time":"2026-01-12T12:00:20+00:00","arrival_time":"2026-01-12T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.29119399999999995,"normal":0.708806},"reference_distribution":{"anomalous":0.8508915676301732,"normal":0.14910843236982685}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-011-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-12T12:00:20+00:00","arrival_time":"2026-01-12T12:00:35+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":11,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"7e5c67095ba5af5d5e8595c0f84d04f647683c4b525077a05203b166238fb8a9"}}
{"id":"evaluation-v1-justified_revision-20260725-012","name":"Evaluation v1.0 trajectory: justified_revision case 012","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-012","label":"Distractor 012","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7684,"modality":"semantic_status","timestamp":"2026-01-13T12:00:10Z","metadata":{"arrival_time":"2026-01-13T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-012","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.72,"modality":"semantic_status","timestamp":"2026-01-13T12:00:12Z","metadata":{"arrival_time":"2026-01-13T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.9672,"modality":"semantic_status","timestamp":"2026-01-13T12:00:20Z","metadata":{"arrival_time":"2026-01-13T12:00:36+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-13T12:00:10+00:00","obs-distractor":"2026-01-13T12:00:12+00:00","obs-2":"2026-01-13T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-13T12:00:10+00:00","obs-distractor":"2026-01-13T12:00:12+00:00","obs-2":"2026-01-13T12:00:36+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.934,"edge-ai-1":0.652},"confidence":{"obs-1":0.7684,"obs-distractor":0.72,"obs-2":0.9672},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-012-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6870893588129777,"event_time":"2026-01-13T12:00:20+00:00","arrival_time":"2026-01-13T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24931440000000005,"normal":0.7506856},"reference_distribution":{"anomalous":0.6870893588129777,"normal":0.31291064118702233}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7506856,"event_time":"2026-01-13T12:00:10+00:00","arrival_time":"2026-01-13T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.24931440000000005,"normal":0.7506856}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-13T12:00:10+00:00","arrival_time":"2026-01-13T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7506856,"event_time":"2026-01-13T12:00:12+00:00","arrival_time":"2026-01-13T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24931440000000005,"normal":0.7506856},"reference_distribution":{"anomalous":0.24931440000000005,"normal":0.7506856}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-13T12:00:12+00:00","arrival_time":"2026-01-13T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6870893588129777,"event_time":"2026-01-13T12:00:20+00:00","arrival_time":"2026-01-13T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24931440000000005,"normal":0.7506856},"reference_distribution":{"anomalous":0.6870893588129777,"normal":0.31291064118702233}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-012-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-13T12:00:20+00:00","arrival_time":"2026-01-13T12:00:36+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":12,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"0bded7cb651b09e01452fe7ecc1142a1f71ff29032757bdd069ec815fc7614c5"}}
{"id":"evaluation-v1-justified_revision-20260725-013","name":"Evaluation v1.0 trajectory: justified_revision case 013","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-013","label":"Distractor 013","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7691,"modality":"semantic_status","timestamp":"2026-01-14T12:00:10Z","metadata":{"arrival_time":"2026-01-14T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-013","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.73,"modality":"semantic_status","timestamp":"2026-01-14T12:00:13Z","metadata":{"arrival_time":"2026-01-14T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.966967,"modality":"semantic_status","timestamp":"2026-01-14T12:00:20Z","metadata":{"arrival_time":"2026-01-14T12:00:37+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-14T12:00:10+00:00","obs-distractor":"2026-01-14T12:00:13+00:00","obs-2":"2026-01-14T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-14T12:00:10+00:00","obs-distractor":"2026-01-14T12:00:13+00:00","obs-2":"2026-01-14T12:00:37+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.942,"edge-ai-1":0.52},"confidence":{"obs-1":0.7691,"obs-distractor":0.73,"obs-2":0.966967},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-013-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8618730254976389,"event_time":"2026-01-14T12:00:20+00:00","arrival_time":"2026-01-14T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2852582,"normal":0.7147418},"reference_distribution":{"anomalous":0.8618730254976389,"normal":0.13812697450236117}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7147418,"event_time":"2026-01-14T12:00:10+00:00","arrival_time":"2026-01-14T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2852582,"normal":0.7147418}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-14T12:00:10+00:00","arrival_time":"2026-01-14T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7147418,"event_time":"2026-01-14T12:00:13+00:00","arrival_time":"2026-01-14T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2852582,"normal":0.7147418},"reference_distribution":{"anomalous":0.2852582,"normal":0.7147418}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-14T12:00:13+00:00","arrival_time":"2026-01-14T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8618730254976389,"event_time":"2026-01-14T12:00:20+00:00","arrival_time":"2026-01-14T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2852582,"normal":0.7147418},"reference_distribution":{"anomalous":0.8618730254976389,"normal":0.13812697450236117}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-013-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-14T12:00:20+00:00","arrival_time":"2026-01-14T12:00:37+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":13,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"3fcfc5fc41d706c102fd1ad32044efbd148d76821b07d85ef1ed1e680555ca93"}}
{"id":"evaluation-v1-justified_revision-20260725-014","name":"Evaluation v1.0 trajectory: justified_revision case 014","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-014","label":"Distractor 014","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7698,"modality":"semantic_status","timestamp":"2026-01-15T12:00:10Z","metadata":{"arrival_time":"2026-01-15T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.966733,"modality":"semantic_status","timestamp":"2026-01-15T12:00:20Z","metadata":{"arrival_time":"2026-01-15T12:00:38+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-014","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.74,"modality":"semantic_status","timestamp":"2026-01-15T12:00:14Z","metadata":{"arrival_time":"2026-01-15T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-15T12:00:10+00:00","obs-2":"2026-01-15T12:00:20+00:00","obs-distractor":"2026-01-15T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-15T12:00:10+00:00","obs-2":"2026-01-15T12:00:38+00:00","obs-distractor":"2026-01-15T12:00:14+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.95,"edge-ai-1":0.531},"confidence":{"obs-1":0.7698,"obs-2":0.966733,"obs-distractor":0.74},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-014-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.696050409183848,"event_time":"2026-01-15T12:00:20+00:00","arrival_time":"2026-01-15T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24368999999999996,"normal":0.75631},"reference_distribution":{"anomalous":0.696050409183848,"normal":0.3039495908161521}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.75631,"event_time":"2026-01-15T12:00:10+00:00","arrival_time":"2026-01-15T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.24368999999999996,"normal":0.75631}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-15T12:00:10+00:00","arrival_time":"2026-01-15T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.75631,"event_time":"2026-01-15T12:00:14+00:00","arrival_time":"2026-01-15T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24368999999999996,"normal":0.75631},"reference_distribution":{"anomalous":0.24368999999999996,"normal":0.75631}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-15T12:00:14+00:00","arrival_time":"2026-01-15T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.696050409183848,"event_time":"2026-01-15T12:00:20+00:00","arrival_time":"2026-01-15T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24368999999999996,"normal":0.75631},"reference_distribution":{"anomalous":0.696050409183848,"normal":0.3039495908161521}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-014-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-15T12:00:20+00:00","arrival_time":"2026-01-15T12:00:38+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":14,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"b4e90e64dde2a14bd071ad30182ed97e8db8e38c5567ba207c545d5ec7d5255d"}}
{"id":"evaluation-v1-justified_revision-20260725-015","name":"Evaluation v1.0 trajectory: justified_revision case 015","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-015","label":"Distractor 015","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7705,"modality":"semantic_status","timestamp":"2026-01-16T12:00:10Z","metadata":{"arrival_time":"2026-01-16T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.9665,"modality":"semantic_status","timestamp":"2026-01-16T12:00:20Z","metadata":{"arrival_time":"2026-01-16T12:00:39+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-015","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.75,"modality":"semantic_status","timestamp":"2026-01-16T12:00:12Z","metadata":{"arrival_time":"2026-01-16T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-16T12:00:10+00:00","obs-2":"2026-01-16T12:00:20+00:00","obs-distractor":"2026-01-16T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-16T12:00:10+00:00","obs-2":"2026-01-16T12:00:39+00:00","obs-distractor":"2026-01-16T12:00:12+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.958,"edge-ai-1":0.542},"confidence":{"obs-1":0.7705,"obs-2":0.9665,"obs-distractor":0.75},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-015-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8735899591589784,"event_time":"2026-01-16T12:00:20+00:00","arrival_time":"2026-01-16T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2792720000000001,"normal":0.7207279999999999},"reference_distribution":{"anomalous":0.8735899591589784,"normal":0.1264100408410215}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7207279999999999,"event_time":"2026-01-16T12:00:10+00:00","arrival_time":"2026-01-16T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2792720000000001,"normal":0.7207279999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-16T12:00:10+00:00","arrival_time":"2026-01-16T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7207279999999999,"event_time":"2026-01-16T12:00:12+00:00","arrival_time":"2026-01-16T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2792720000000001,"normal":0.7207279999999999},"reference_distribution":{"anomalous":0.2792720000000001,"normal":0.7207279999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-16T12:00:12+00:00","arrival_time":"2026-01-16T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8735899591589784,"event_time":"2026-01-16T12:00:20+00:00","arrival_time":"2026-01-16T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2792720000000001,"normal":0.7207279999999999},"reference_distribution":{"anomalous":0.8735899591589784,"normal":0.1264100408410215}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-015-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-16T12:00:20+00:00","arrival_time":"2026-01-16T12:00:39+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":15,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"bf3c64457c9019464e695b1896ae44e94ce0d298813e0d275f7f6bd60feaea49"}}
{"id":"evaluation-v1-justified_revision-20260725-016","name":"Evaluation v1.0 trajectory: justified_revision case 016","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-016","label":"Distractor 016","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7712,"modality":"semantic_status","timestamp":"2026-01-17T12:00:10Z","metadata":{"arrival_time":"2026-01-17T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.966267,"modality":"semantic_status","timestamp":"2026-01-17T12:00:20Z","metadata":{"arrival_time":"2026-01-17T12:00:40+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-016","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.76,"modality":"semantic_status","timestamp":"2026-01-17T12:00:13Z","metadata":{"arrival_time":"2026-01-17T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-17T12:00:10+00:00","obs-2":"2026-01-17T12:00:20+00:00","obs-distractor":"2026-01-17T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-17T12:00:10+00:00","obs-2":"2026-01-17T12:00:40+00:00","obs-distractor":"2026-01-17T12:00:13+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.966,"edge-ai-1":0.553},"confidence":{"obs-1":0.7712,"obs-2":0.966267,"obs-distractor":0.76},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-016-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7055479599326564,"event_time":"2026-01-17T12:00:20+00:00","arrival_time":"2026-01-17T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23802080000000003,"normal":0.7619792},"reference_distribution":{"anomalous":0.7055479599326564,"normal":0.29445204006734355}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7619792,"event_time":"2026-01-17T12:00:10+00:00","arrival_time":"2026-01-17T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.23802080000000003,"normal":0.7619792}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-17T12:00:10+00:00","arrival_time":"2026-01-17T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7619792,"event_time":"2026-01-17T12:00:13+00:00","arrival_time":"2026-01-17T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23802080000000003,"normal":0.7619792},"reference_distribution":{"anomalous":0.23802080000000003,"normal":0.7619792}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-17T12:00:13+00:00","arrival_time":"2026-01-17T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7055479599326564,"event_time":"2026-01-17T12:00:20+00:00","arrival_time":"2026-01-17T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23802080000000003,"normal":0.7619792},"reference_distribution":{"anomalous":0.7055479599326564,"normal":0.29445204006734355}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-016-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-17T12:00:20+00:00","arrival_time":"2026-01-17T12:00:40+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":16,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"b19f7ed3308ee0f3ac7da1253ac4b5f7796b57fe3dcdb572ec20a0fe461b2fe7"}}
{"id":"evaluation-v1-justified_revision-20260725-017","name":"Evaluation v1.0 trajectory: justified_revision case 017","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-017","label":"Distractor 017","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7719,"modality":"semantic_status","timestamp":"2026-01-18T12:00:10Z","metadata":{"arrival_time":"2026-01-18T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-017","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.77,"modality":"semantic_status","timestamp":"2026-01-18T12:00:14Z","metadata":{"arrival_time":"2026-01-18T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.966033,"modality":"semantic_status","timestamp":"2026-01-18T12:00:20Z","metadata":{"arrival_time":"2026-01-18T12:00:24+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-18T12:00:10+00:00","obs-distractor":"2026-01-18T12:00:14+00:00","obs-2":"2026-01-18T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-18T12:00:10+00:00","obs-distractor":"2026-01-18T12:00:14+00:00","obs-2":"2026-01-18T12:00:24+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.974,"edge-ai-1":0.564},"confidence":{"obs-1":0.7719,"obs-distractor":0.77,"obs-2":0.966033},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-017-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8861338217115141,"event_time":"2026-01-18T12:00:20+00:00","arrival_time":"2026-01-18T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2732354,"normal":0.7267646},"reference_distribution":{"anomalous":0.8861338217115141,"normal":0.11386617828848597}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7267646,"event_time":"2026-01-18T12:00:10+00:00","arrival_time":"2026-01-18T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2732354,"normal":0.7267646}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-18T12:00:10+00:00","arrival_time":"2026-01-18T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7267646,"event_time":"2026-01-18T12:00:14+00:00","arrival_time":"2026-01-18T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2732354,"normal":0.7267646},"reference_distribution":{"anomalous":0.2732354,"normal":0.7267646}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-18T12:00:14+00:00","arrival_time":"2026-01-18T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8861338217115141,"event_time":"2026-01-18T12:00:20+00:00","arrival_time":"2026-01-18T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2732354,"normal":0.7267646},"reference_distribution":{"anomalous":0.8861338217115141,"normal":0.11386617828848597}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-017-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-18T12:00:20+00:00","arrival_time":"2026-01-18T12:00:24+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":17,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"2c99bae28f0ed6a3eefe6cc8ac2110e848adcbd18dfba1707c629531e597117f"}}
{"id":"evaluation-v1-justified_revision-20260725-018","name":"Evaluation v1.0 trajectory: justified_revision case 018","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-018","label":"Distractor 018","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7726,"modality":"semantic_status","timestamp":"2026-01-19T12:00:10Z","metadata":{"arrival_time":"2026-01-19T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-018","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.78,"modality":"semantic_status","timestamp":"2026-01-19T12:00:12Z","metadata":{"arrival_time":"2026-01-19T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.9658,"modality":"semantic_status","timestamp":"2026-01-19T12:00:20Z","metadata":{"arrival_time":"2026-01-19T12:00:25+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-19T12:00:10+00:00","obs-distractor":"2026-01-19T12:00:12+00:00","obs-2":"2026-01-19T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-19T12:00:10+00:00","obs-distractor":"2026-01-19T12:00:12+00:00","obs-2":"2026-01-19T12:00:25+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.91,"edge-ai-1":0.575},"confidence":{"obs-1":0.7726,"obs-distractor":0.78,"obs-2":0.9658},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-018-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7369117174921741,"event_time":"2026-01-19T12:00:20+00:00","arrival_time":"2026-01-19T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2519340000000001,"normal":0.7480659999999999},"reference_distribution":{"anomalous":0.7369117174921741,"normal":0.2630882825078258}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7480659999999999,"event_time":"2026-01-19T12:00:10+00:00","arrival_time":"2026-01-19T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2519340000000001,"normal":0.7480659999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-19T12:00:10+00:00","arrival_time":"2026-01-19T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7480659999999999,"event_time":"2026-01-19T12:00:12+00:00","arrival_time":"2026-01-19T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2519340000000001,"normal":0.7480659999999999},"reference_distribution":{"anomalous":0.2519340000000001,"normal":0.7480659999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-19T12:00:12+00:00","arrival_time":"2026-01-19T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7369117174921741,"event_time":"2026-01-19T12:00:20+00:00","arrival_time":"2026-01-19T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2519340000000001,"normal":0.7480659999999999},"reference_distribution":{"anomalous":0.7369117174921741,"normal":0.2630882825078258}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-018-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-19T12:00:20+00:00","arrival_time":"2026-01-19T12:00:25+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":18,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"85c10e05cc136c0783b051ca4343cf06c3549f43c8a3cb888e9a7c6ebaca4d99"}}
{"id":"evaluation-v1-justified_revision-20260725-019","name":"Evaluation v1.0 trajectory: justified_revision case 019","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-019","label":"Distractor 019","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7733,"modality":"semantic_status","timestamp":"2026-01-20T12:00:10Z","metadata":{"arrival_time":"2026-01-20T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.965567,"modality":"semantic_status","timestamp":"2026-01-20T12:00:20Z","metadata":{"arrival_time":"2026-01-20T12:00:26+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-019","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.79,"modality":"semantic_status","timestamp":"2026-01-20T12:00:13Z","metadata":{"arrival_time":"2026-01-20T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-20T12:00:10+00:00","obs-2":"2026-01-20T12:00:20+00:00","obs-distractor":"2026-01-20T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-20T12:00:10+00:00","obs-2":"2026-01-20T12:00:26+00:00","obs-distractor":"2026-01-20T12:00:13+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.918,"edge-ai-1":0.586},"confidence":{"obs-1":0.7733,"obs-2":0.965567,"obs-distractor":0.79},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-019-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8231941926995308,"event_time":"2026-01-20T12:00:20+00:00","arrival_time":"2026-01-20T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26714839999999995,"normal":0.7328516},"reference_distribution":{"anomalous":0.8231941926995308,"normal":0.17680580730046916}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7328516,"event_time":"2026-01-20T12:00:10+00:00","arrival_time":"2026-01-20T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.26714839999999995,"normal":0.7328516}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-20T12:00:10+00:00","arrival_time":"2026-01-20T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7328516,"event_time":"2026-01-20T12:00:13+00:00","arrival_time":"2026-01-20T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26714839999999995,"normal":0.7328516},"reference_distribution":{"anomalous":0.26714839999999995,"normal":0.7328516}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-20T12:00:13+00:00","arrival_time":"2026-01-20T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8231941926995308,"event_time":"2026-01-20T12:00:20+00:00","arrival_time":"2026-01-20T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26714839999999995,"normal":0.7328516},"reference_distribution":{"anomalous":0.8231941926995308,"normal":0.17680580730046916}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-019-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-20T12:00:20+00:00","arrival_time":"2026-01-20T12:00:26+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":19,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"759f82e528a9338f2f48a828da4605eef840c06fbca3e0ddbbeeb728f8d46be6"}}
{"id":"evaluation-v1-justified_revision-20260725-020","name":"Evaluation v1.0 trajectory: justified_revision case 020","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-020","label":"Distractor 020","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.774,"modality":"semantic_status","timestamp":"2026-01-21T12:00:10Z","metadata":{"arrival_time":"2026-01-21T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-020","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-01-21T12:00:14Z","metadata":{"arrival_time":"2026-01-21T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.965333,"modality":"semantic_status","timestamp":"2026-01-21T12:00:20Z","metadata":{"arrival_time":"2026-01-21T12:00:27+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-21T12:00:10+00:00","obs-distractor":"2026-01-21T12:00:14+00:00","obs-2":"2026-01-21T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-21T12:00:10+00:00","obs-distractor":"2026-01-21T12:00:14+00:00","obs-2":"2026-01-21T12:00:27+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.926,"edge-ai-1":0.597},"confidence":{"obs-1":0.774,"obs-distractor":0.6,"obs-2":0.965333},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-020-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7476114271747702,"event_time":"2026-01-21T12:00:20+00:00","arrival_time":"2026-01-21T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24627599999999994,"normal":0.7537240000000001},"reference_distribution":{"anomalous":0.7476114271747702,"normal":0.2523885728252298}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7537240000000001,"event_time":"2026-01-21T12:00:10+00:00","arrival_time":"2026-01-21T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.24627599999999994,"normal":0.7537240000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-21T12:00:10+00:00","arrival_time":"2026-01-21T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7537240000000001,"event_time":"2026-01-21T12:00:14+00:00","arrival_time":"2026-01-21T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24627599999999994,"normal":0.7537240000000001},"reference_distribution":{"anomalous":0.24627599999999994,"normal":0.7537240000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-21T12:00:14+00:00","arrival_time":"2026-01-21T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7476114271747702,"event_time":"2026-01-21T12:00:20+00:00","arrival_time":"2026-01-21T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24627599999999994,"normal":0.7537240000000001},"reference_distribution":{"anomalous":0.7476114271747702,"normal":0.2523885728252298}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-020-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-21T12:00:20+00:00","arrival_time":"2026-01-21T12:00:27+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":20,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"249eba939c435017f3138812f59b94e69025ecb7ba6661a29ea5c69a09a223d4"}}
{"id":"evaluation-v1-justified_revision-20260725-021","name":"Evaluation v1.0 trajectory: justified_revision case 021","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-021","label":"Distractor 021","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7747,"modality":"semantic_status","timestamp":"2026-01-22T12:00:10Z","metadata":{"arrival_time":"2026-01-22T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-021","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-01-22T12:00:12Z","metadata":{"arrival_time":"2026-01-22T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.9651,"modality":"semantic_status","timestamp":"2026-01-22T12:00:20Z","metadata":{"arrival_time":"2026-01-22T12:00:28+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-22T12:00:10+00:00","obs-distractor":"2026-01-22T12:00:12+00:00","obs-2":"2026-01-22T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-22T12:00:10+00:00","obs-distractor":"2026-01-22T12:00:12+00:00","obs-2":"2026-01-22T12:00:28+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.934,"edge-ai-1":0.608},"confidence":{"obs-1":0.7747,"obs-distractor":0.61,"obs-2":0.9651},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-021-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8341962604048994,"event_time":"2026-01-22T12:00:20+00:00","arrival_time":"2026-01-22T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.261011,"normal":0.738989},"reference_distribution":{"anomalous":0.8341962604048994,"normal":0.1658037395951006}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.738989,"event_time":"2026-01-22T12:00:10+00:00","arrival_time":"2026-01-22T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.261011,"normal":0.738989}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-22T12:00:10+00:00","arrival_time":"2026-01-22T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.738989,"event_time":"2026-01-22T12:00:12+00:00","arrival_time":"2026-01-22T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.261011,"normal":0.738989},"reference_distribution":{"anomalous":0.261011,"normal":0.738989}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-22T12:00:12+00:00","arrival_time":"2026-01-22T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8341962604048994,"event_time":"2026-01-22T12:00:20+00:00","arrival_time":"2026-01-22T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.261011,"normal":0.738989},"reference_distribution":{"anomalous":0.8341962604048994,"normal":0.1658037395951006}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-021-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-22T12:00:20+00:00","arrival_time":"2026-01-22T12:00:28+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":21,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"9a78ea62dafcac3ba05c2a6332746b75c897d292ee99ca0e4721ba9ff63d1239"}}
{"id":"evaluation-v1-justified_revision-20260725-022","name":"Evaluation v1.0 trajectory: justified_revision case 022","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-022","label":"Distractor 022","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7754,"modality":"semantic_status","timestamp":"2026-01-23T12:00:10Z","metadata":{"arrival_time":"2026-01-23T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-022","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-01-23T12:00:13Z","metadata":{"arrival_time":"2026-01-23T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.964867,"modality":"semantic_status","timestamp":"2026-01-23T12:00:20Z","metadata":{"arrival_time":"2026-01-23T12:00:29+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-23T12:00:10+00:00","obs-distractor":"2026-01-23T12:00:13+00:00","obs-2":"2026-01-23T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-23T12:00:10+00:00","obs-distractor":"2026-01-23T12:00:13+00:00","obs-2":"2026-01-23T12:00:29+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.942,"edge-ai-1":0.619},"confidence":{"obs-1":0.7754,"obs-distractor":0.62,"obs-2":0.964867},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-022-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6654069119505603,"event_time":"2026-01-23T12:00:20+00:00","arrival_time":"2026-01-23T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24057320000000004,"normal":0.7594268},"reference_distribution":{"anomalous":0.6654069119505603,"normal":0.3345930880494396}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7594268,"event_time":"2026-01-23T12:00:10+00:00","arrival_time":"2026-01-23T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.24057320000000004,"normal":0.7594268}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-23T12:00:10+00:00","arrival_time":"2026-01-23T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7594268,"event_time":"2026-01-23T12:00:13+00:00","arrival_time":"2026-01-23T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24057320000000004,"normal":0.7594268},"reference_distribution":{"anomalous":0.24057320000000004,"normal":0.7594268}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-23T12:00:13+00:00","arrival_time":"2026-01-23T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6654069119505603,"event_time":"2026-01-23T12:00:20+00:00","arrival_time":"2026-01-23T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24057320000000004,"normal":0.7594268},"reference_distribution":{"anomalous":0.6654069119505603,"normal":0.3345930880494396}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-022-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-23T12:00:20+00:00","arrival_time":"2026-01-23T12:00:29+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":22,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"8640f184a36196574598c1f211b9b6b5d7a97491ee542d232b7428839f873ca8"}}
{"id":"evaluation-v1-justified_revision-20260725-023","name":"Evaluation v1.0 trajectory: justified_revision case 023","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-023","label":"Distractor 023","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7761,"modality":"semantic_status","timestamp":"2026-01-24T12:00:10Z","metadata":{"arrival_time":"2026-01-24T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.964633,"modality":"semantic_status","timestamp":"2026-01-24T12:00:20Z","metadata":{"arrival_time":"2026-01-24T12:00:30+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-023","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-01-24T12:00:14Z","metadata":{"arrival_time":"2026-01-24T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-24T12:00:10+00:00","obs-2":"2026-01-24T12:00:20+00:00","obs-distractor":"2026-01-24T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-24T12:00:10+00:00","obs-2":"2026-01-24T12:00:30+00:00","obs-distractor":"2026-01-24T12:00:14+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.95,"edge-ai-1":0.63},"confidence":{"obs-1":0.7761,"obs-2":0.964633,"obs-distractor":0.63},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-023-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8632879218359119,"event_time":"2026-01-24T12:00:20+00:00","arrival_time":"2026-01-24T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.28215710000000005,"normal":0.7178429},"reference_distribution":{"anomalous":0.8632879218359119,"normal":0.1367120781640882}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7178429,"event_time":"2026-01-24T12:00:10+00:00","arrival_time":"2026-01-24T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.28215710000000005,"normal":0.7178429}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-24T12:00:10+00:00","arrival_time":"2026-01-24T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7178429,"event_time":"2026-01-24T12:00:14+00:00","arrival_time":"2026-01-24T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.28215710000000005,"normal":0.7178429},"reference_distribution":{"anomalous":0.28215710000000005,"normal":0.7178429}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-24T12:00:14+00:00","arrival_time":"2026-01-24T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8632879218359119,"event_time":"2026-01-24T12:00:20+00:00","arrival_time":"2026-01-24T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.28215710000000005,"normal":0.7178429},"reference_distribution":{"anomalous":0.8632879218359119,"normal":0.1367120781640882}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-023-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-24T12:00:20+00:00","arrival_time":"2026-01-24T12:00:30+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":23,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"772c75cd99a11683e1f5564901338d45295271a14bdb0df4b231db4dfa7c6ced"}}
{"id":"evaluation-v1-justified_revision-20260725-024","name":"Evaluation v1.0 trajectory: justified_revision case 024","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-024","label":"Distractor 024","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7768,"modality":"semantic_status","timestamp":"2026-01-25T12:00:10Z","metadata":{"arrival_time":"2026-01-25T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-024","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-01-25T12:00:12Z","metadata":{"arrival_time":"2026-01-25T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.9644,"modality":"semantic_status","timestamp":"2026-01-25T12:00:20Z","metadata":{"arrival_time":"2026-01-25T12:00:31+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-25T12:00:10+00:00","obs-distractor":"2026-01-25T12:00:12+00:00","obs-2":"2026-01-25T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-25T12:00:10+00:00","obs-distractor":"2026-01-25T12:00:12+00:00","obs-2":"2026-01-25T12:00:31+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.958,"edge-ai-1":0.641},"confidence":{"obs-1":0.7768,"obs-distractor":0.64,"obs-2":0.9644},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-024-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6736929127092862,"event_time":"2026-01-25T12:00:20+00:00","arrival_time":"2026-01-25T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23482559999999997,"normal":0.7651744},"reference_distribution":{"anomalous":0.6736929127092862,"normal":0.3263070872907138}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7651744,"event_time":"2026-01-25T12:00:10+00:00","arrival_time":"2026-01-25T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.23482559999999997,"normal":0.7651744}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-25T12:00:10+00:00","arrival_time":"2026-01-25T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7651744,"event_time":"2026-01-25T12:00:12+00:00","arrival_time":"2026-01-25T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23482559999999997,"normal":0.7651744},"reference_distribution":{"anomalous":0.23482559999999997,"normal":0.7651744}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-25T12:00:12+00:00","arrival_time":"2026-01-25T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6736929127092862,"event_time":"2026-01-25T12:00:20+00:00","arrival_time":"2026-01-25T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23482559999999997,"normal":0.7651744},"reference_distribution":{"anomalous":0.6736929127092862,"normal":0.3263070872907138}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-024-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-25T12:00:20+00:00","arrival_time":"2026-01-25T12:00:31+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":24,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"388865fbf9ffce08c51ee0656e8881944ab0d23e0583f58a69142edeaef0150a"}}
{"id":"evaluation-v1-justified_revision-20260725-025","name":"Evaluation v1.0 trajectory: justified_revision case 025","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-025","label":"Distractor 025","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7775,"modality":"semantic_status","timestamp":"2026-01-26T12:00:10Z","metadata":{"arrival_time":"2026-01-26T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-025","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-01-26T12:00:13Z","metadata":{"arrival_time":"2026-01-26T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.964167,"modality":"semantic_status","timestamp":"2026-01-26T12:00:20Z","metadata":{"arrival_time":"2026-01-26T12:00:32+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-26T12:00:10+00:00","obs-distractor":"2026-01-26T12:00:13+00:00","obs-2":"2026-01-26T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-26T12:00:10+00:00","obs-distractor":"2026-01-26T12:00:13+00:00","obs-2":"2026-01-26T12:00:32+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.966,"edge-ai-1":0.652},"confidence":{"obs-1":0.7775,"obs-distractor":0.65,"obs-2":0.964167},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-025-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8751029781404251,"event_time":"2026-01-26T12:00:20+00:00","arrival_time":"2026-01-26T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.27605750000000007,"normal":0.7239424999999999},"reference_distribution":{"anomalous":0.8751029781404251,"normal":0.12489702185957481}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7239424999999999,"event_time":"2026-01-26T12:00:10+00:00","arrival_time":"2026-01-26T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.27605750000000007,"normal":0.7239424999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-26T12:00:10+00:00","arrival_time":"2026-01-26T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7239424999999999,"event_time":"2026-01-26T12:00:13+00:00","arrival_time":"2026-01-26T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.27605750000000007,"normal":0.7239424999999999},"reference_distribution":{"anomalous":0.27605750000000007,"normal":0.7239424999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-26T12:00:13+00:00","arrival_time":"2026-01-26T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8751029781404251,"event_time":"2026-01-26T12:00:20+00:00","arrival_time":"2026-01-26T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.27605750000000007,"normal":0.7239424999999999},"reference_distribution":{"anomalous":0.8751029781404251,"normal":0.12489702185957481}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-025-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-26T12:00:20+00:00","arrival_time":"2026-01-26T12:00:32+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":25,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"98540a674a58350cc14291ea17e3fd1972e8f561eb0e7a0908731400d682c0e4"}}
{"id":"evaluation-v1-justified_revision-20260725-026","name":"Evaluation v1.0 trajectory: justified_revision case 026","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-026","label":"Distractor 026","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7782,"modality":"semantic_status","timestamp":"2026-01-27T12:00:10Z","metadata":{"arrival_time":"2026-01-27T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.963933,"modality":"semantic_status","timestamp":"2026-01-27T12:00:20Z","metadata":{"arrival_time":"2026-01-27T12:00:33+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-026","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-01-27T12:00:14Z","metadata":{"arrival_time":"2026-01-27T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-27T12:00:10+00:00","obs-2":"2026-01-27T12:00:20+00:00","obs-distractor":"2026-01-27T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-27T12:00:10+00:00","obs-2":"2026-01-27T12:00:33+00:00","obs-distractor":"2026-01-27T12:00:14+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.974,"edge-ai-1":0.52},"confidence":{"obs-1":0.7782,"obs-2":0.963933,"obs-distractor":0.66},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-026-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6824757888671524,"event_time":"2026-01-27T12:00:20+00:00","arrival_time":"2026-01-27T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22903319999999994,"normal":0.7709668000000001},"reference_distribution":{"anomalous":0.6824757888671524,"normal":0.3175242111328476}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7709668000000001,"event_time":"2026-01-27T12:00:10+00:00","arrival_time":"2026-01-27T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.22903319999999994,"normal":0.7709668000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-27T12:00:10+00:00","arrival_time":"2026-01-27T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7709668000000001,"event_time":"2026-01-27T12:00:14+00:00","arrival_time":"2026-01-27T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22903319999999994,"normal":0.7709668000000001},"reference_distribution":{"anomalous":0.22903319999999994,"normal":0.7709668000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-27T12:00:14+00:00","arrival_time":"2026-01-27T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6824757888671524,"event_time":"2026-01-27T12:00:20+00:00","arrival_time":"2026-01-27T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22903319999999994,"normal":0.7709668000000001},"reference_distribution":{"anomalous":0.6824757888671524,"normal":0.3175242111328476}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-026-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-27T12:00:20+00:00","arrival_time":"2026-01-27T12:00:33+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":26,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"285a4ddaaf07de875192ac3497befce0b8eeb7832cc3e6b5fd442ed3cf4650db"}}
{"id":"evaluation-v1-justified_revision-20260725-027","name":"Evaluation v1.0 trajectory: justified_revision case 027","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-027","label":"Distractor 027","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7789,"modality":"semantic_status","timestamp":"2026-01-28T12:00:10Z","metadata":{"arrival_time":"2026-01-28T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.9637,"modality":"semantic_status","timestamp":"2026-01-28T12:00:20Z","metadata":{"arrival_time":"2026-01-28T12:00:34+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-027","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-01-28T12:00:12Z","metadata":{"arrival_time":"2026-01-28T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-28T12:00:10+00:00","obs-2":"2026-01-28T12:00:20+00:00","obs-distractor":"2026-01-28T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-28T12:00:10+00:00","obs-2":"2026-01-28T12:00:34+00:00","obs-distractor":"2026-01-28T12:00:12+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.91,"edge-ai-1":0.531},"confidence":{"obs-1":0.7789,"obs-2":0.9637,"obs-distractor":0.67},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-027-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8137079154427075,"event_time":"2026-01-28T12:00:20+00:00","arrival_time":"2026-01-28T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26990749999999997,"normal":0.7300925},"reference_distribution":{"anomalous":0.8137079154427075,"normal":0.1862920845572926}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7300925,"event_time":"2026-01-28T12:00:10+00:00","arrival_time":"2026-01-28T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.26990749999999997,"normal":0.7300925}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-28T12:00:10+00:00","arrival_time":"2026-01-28T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7300925,"event_time":"2026-01-28T12:00:12+00:00","arrival_time":"2026-01-28T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26990749999999997,"normal":0.7300925},"reference_distribution":{"anomalous":0.26990749999999997,"normal":0.7300925}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-28T12:00:12+00:00","arrival_time":"2026-01-28T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8137079154427075,"event_time":"2026-01-28T12:00:20+00:00","arrival_time":"2026-01-28T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26990749999999997,"normal":0.7300925},"reference_distribution":{"anomalous":0.8137079154427075,"normal":0.1862920845572926}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-027-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-28T12:00:20+00:00","arrival_time":"2026-01-28T12:00:34+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":27,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"9d5f667ef737f0cfa5afe01ee4e3a40586dc8d98f02f7e33b84dfd33a131d08d"}}
{"id":"evaluation-v1-justified_revision-20260725-028","name":"Evaluation v1.0 trajectory: justified_revision case 028","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-028","label":"Distractor 028","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7796,"modality":"semantic_status","timestamp":"2026-01-29T12:00:10Z","metadata":{"arrival_time":"2026-01-29T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.963467,"modality":"semantic_status","timestamp":"2026-01-29T12:00:20Z","metadata":{"arrival_time":"2026-01-29T12:00:35+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-028","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-01-29T12:00:13Z","metadata":{"arrival_time":"2026-01-29T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-29T12:00:10+00:00","obs-2":"2026-01-29T12:00:20+00:00","obs-distractor":"2026-01-29T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-29T12:00:10+00:00","obs-2":"2026-01-29T12:00:35+00:00","obs-distractor":"2026-01-29T12:00:13+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.918,"edge-ai-1":0.542},"confidence":{"obs-1":0.7796,"obs-2":0.963467,"obs-distractor":0.68},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-028-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7153002535714326,"event_time":"2026-01-29T12:00:20+00:00","arrival_time":"2026-01-29T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24332719999999997,"normal":0.7566728},"reference_distribution":{"anomalous":0.7153002535714326,"normal":0.2846997464285675}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7566728,"event_time":"2026-01-29T12:00:10+00:00","arrival_time":"2026-01-29T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.24332719999999997,"normal":0.7566728}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-29T12:00:10+00:00","arrival_time":"2026-01-29T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7566728,"event_time":"2026-01-29T12:00:13+00:00","arrival_time":"2026-01-29T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24332719999999997,"normal":0.7566728},"reference_distribution":{"anomalous":0.24332719999999997,"normal":0.7566728}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-29T12:00:13+00:00","arrival_time":"2026-01-29T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7153002535714326,"event_time":"2026-01-29T12:00:20+00:00","arrival_time":"2026-01-29T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24332719999999997,"normal":0.7566728},"reference_distribution":{"anomalous":0.7153002535714326,"normal":0.2846997464285675}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-028-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-29T12:00:20+00:00","arrival_time":"2026-01-29T12:00:35+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":28,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"022b4d002354cb2d07b3335757700cbabe4d127e2a470c03fd8f3deffefd1e95"}}
{"id":"evaluation-v1-justified_revision-20260725-029","name":"Evaluation v1.0 trajectory: justified_revision case 029","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-029","label":"Distractor 029","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7803,"modality":"semantic_status","timestamp":"2026-01-30T12:00:10Z","metadata":{"arrival_time":"2026-01-30T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-029","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-01-30T12:00:14Z","metadata":{"arrival_time":"2026-01-30T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.963233,"modality":"semantic_status","timestamp":"2026-01-30T12:00:20Z","metadata":{"arrival_time":"2026-01-30T12:00:36+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-30T12:00:10+00:00","obs-distractor":"2026-01-30T12:00:14+00:00","obs-2":"2026-01-30T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-30T12:00:10+00:00","obs-distractor":"2026-01-30T12:00:14+00:00","obs-2":"2026-01-30T12:00:36+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.926,"edge-ai-1":0.553},"confidence":{"obs-1":0.7803,"obs-distractor":0.69,"obs-2":0.963233},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-029-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8240366129250046,"event_time":"2026-01-30T12:00:20+00:00","arrival_time":"2026-01-30T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26370709999999997,"normal":0.7362929},"reference_distribution":{"anomalous":0.8240366129250046,"normal":0.17596338707499534}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7362929,"event_time":"2026-01-30T12:00:10+00:00","arrival_time":"2026-01-30T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.26370709999999997,"normal":0.7362929}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-30T12:00:10+00:00","arrival_time":"2026-01-30T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7362929,"event_time":"2026-01-30T12:00:14+00:00","arrival_time":"2026-01-30T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26370709999999997,"normal":0.7362929},"reference_distribution":{"anomalous":0.26370709999999997,"normal":0.7362929}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-30T12:00:14+00:00","arrival_time":"2026-01-30T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8240366129250046,"event_time":"2026-01-30T12:00:20+00:00","arrival_time":"2026-01-30T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26370709999999997,"normal":0.7362929},"reference_distribution":{"anomalous":0.8240366129250046,"normal":0.17596338707499534}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-029-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-30T12:00:20+00:00","arrival_time":"2026-01-30T12:00:36+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":29,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"51bec71eeb95151694b902b95c29d71aea137a5f6b9c4dce25bfc80b8c6e59d0"}}
{"id":"evaluation-v1-justified_revision-20260725-030","name":"Evaluation v1.0 trajectory: justified_revision case 030","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-030","label":"Distractor 030","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.781,"modality":"semantic_status","timestamp":"2026-01-31T12:00:10Z","metadata":{"arrival_time":"2026-01-31T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.963,"modality":"semantic_status","timestamp":"2026-01-31T12:00:20Z","metadata":{"arrival_time":"2026-01-31T12:00:37+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-030","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.7,"modality":"semantic_status","timestamp":"2026-01-31T12:00:12Z","metadata":{"arrival_time":"2026-01-31T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-31T12:00:10+00:00","obs-2":"2026-01-31T12:00:20+00:00","obs-distractor":"2026-01-31T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-31T12:00:10+00:00","obs-2":"2026-01-31T12:00:37+00:00","obs-distractor":"2026-01-31T12:00:12+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.934,"edge-ai-1":0.564},"confidence":{"obs-1":0.781,"obs-2":0.963,"obs-distractor":0.7},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-030-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7253424355921991,"event_time":"2026-01-31T12:00:20+00:00","arrival_time":"2026-01-31T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23754600000000003,"normal":0.762454},"reference_distribution":{"anomalous":0.7253424355921991,"normal":0.27465756440780087}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.762454,"event_time":"2026-01-31T12:00:10+00:00","arrival_time":"2026-01-31T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.23754600000000003,"normal":0.762454}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-31T12:00:10+00:00","arrival_time":"2026-01-31T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.762454,"event_time":"2026-01-31T12:00:12+00:00","arrival_time":"2026-01-31T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23754600000000003,"normal":0.762454},"reference_distribution":{"anomalous":0.23754600000000003,"normal":0.762454}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-31T12:00:12+00:00","arrival_time":"2026-01-31T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7253424355921991,"event_time":"2026-01-31T12:00:20+00:00","arrival_time":"2026-01-31T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23754600000000003,"normal":0.762454},"reference_distribution":{"anomalous":0.7253424355921991,"normal":0.27465756440780087}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-030-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-31T12:00:20+00:00","arrival_time":"2026-01-31T12:00:37+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":30,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"98f3d49aeb1ee1fcbdb764053d87fd82c00e2c79d41abaa748d08b8924ffa2b4"}}
{"id":"evaluation-v1-justified_revision-20260725-031","name":"Evaluation v1.0 trajectory: justified_revision case 031","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-031","label":"Distractor 031","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7817,"modality":"semantic_status","timestamp":"2026-02-01T12:00:10Z","metadata":{"arrival_time":"2026-02-01T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-031","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.71,"modality":"semantic_status","timestamp":"2026-02-01T12:00:13Z","metadata":{"arrival_time":"2026-02-01T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.962767,"modality":"semantic_status","timestamp":"2026-02-01T12:00:20Z","metadata":{"arrival_time":"2026-02-01T12:00:38+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-01T12:00:10+00:00","obs-distractor":"2026-02-01T12:00:13+00:00","obs-2":"2026-02-01T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-01T12:00:10+00:00","obs-distractor":"2026-02-01T12:00:13+00:00","obs-2":"2026-02-01T12:00:38+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.942,"edge-ai-1":0.575},"confidence":{"obs-1":0.7817,"obs-distractor":0.71,"obs-2":0.962767},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-031-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8351085850197303,"event_time":"2026-02-01T12:00:20+00:00","arrival_time":"2026-02-01T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2574563000000001,"normal":0.7425436999999999},"reference_distribution":{"anomalous":0.8351085850197303,"normal":0.16489141498026974}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7425436999999999,"event_time":"2026-02-01T12:00:10+00:00","arrival_time":"2026-02-01T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2574563000000001,"normal":0.7425436999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-01T12:00:10+00:00","arrival_time":"2026-02-01T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7425436999999999,"event_time":"2026-02-01T12:00:13+00:00","arrival_time":"2026-02-01T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2574563000000001,"normal":0.7425436999999999},"reference_distribution":{"anomalous":0.2574563000000001,"normal":0.7425436999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-01T12:00:13+00:00","arrival_time":"2026-02-01T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8351085850197303,"event_time":"2026-02-01T12:00:20+00:00","arrival_time":"2026-02-01T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2574563000000001,"normal":0.7425436999999999},"reference_distribution":{"anomalous":0.8351085850197303,"normal":0.16489141498026974}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-031-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-01T12:00:20+00:00","arrival_time":"2026-02-01T12:00:38+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":31,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"8e037b2b0eb24e565799b228bf138d2f17565a6899cef3a04229360500c9130c"}}
{"id":"evaluation-v1-justified_revision-20260725-032","name":"Evaluation v1.0 trajectory: justified_revision case 032","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-032","label":"Distractor 032","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7824,"modality":"semantic_status","timestamp":"2026-02-02T12:00:10Z","metadata":{"arrival_time":"2026-02-02T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.962533,"modality":"semantic_status","timestamp":"2026-02-02T12:00:20Z","metadata":{"arrival_time":"2026-02-02T12:00:39+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-032","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.72,"modality":"semantic_status","timestamp":"2026-02-02T12:00:14Z","metadata":{"arrival_time":"2026-02-02T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-02T12:00:10+00:00","obs-2":"2026-02-02T12:00:20+00:00","obs-distractor":"2026-02-02T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-02T12:00:10+00:00","obs-2":"2026-02-02T12:00:39+00:00","obs-distractor":"2026-02-02T12:00:14+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.95,"edge-ai-1":0.586},"confidence":{"obs-1":0.7824,"obs-2":0.962533,"obs-distractor":0.72},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-032-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7360615882448638,"event_time":"2026-02-02T12:00:20+00:00","arrival_time":"2026-02-02T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23172000000000004,"normal":0.76828},"reference_distribution":{"anomalous":0.7360615882448638,"normal":0.26393841175513616}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.76828,"event_time":"2026-02-02T12:00:10+00:00","arrival_time":"2026-02-02T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.23172000000000004,"normal":0.76828}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-02T12:00:10+00:00","arrival_time":"2026-02-02T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.76828,"event_time":"2026-02-02T12:00:14+00:00","arrival_time":"2026-02-02T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23172000000000004,"normal":0.76828},"reference_distribution":{"anomalous":0.23172000000000004,"normal":0.76828}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-02T12:00:14+00:00","arrival_time":"2026-02-02T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7360615882448638,"event_time":"2026-02-02T12:00:20+00:00","arrival_time":"2026-02-02T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23172000000000004,"normal":0.76828},"reference_distribution":{"anomalous":0.7360615882448638,"normal":0.26393841175513616}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-032-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-02T12:00:20+00:00","arrival_time":"2026-02-02T12:00:39+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":32,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"0b5da445be64a4a372415ea616a9e6b57b7cfd8f23b019ec614517beebad69d4"}}
{"id":"evaluation-v1-justified_revision-20260725-033","name":"Evaluation v1.0 trajectory: justified_revision case 033","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-033","label":"Distractor 033","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7831,"modality":"semantic_status","timestamp":"2026-02-03T12:00:10Z","metadata":{"arrival_time":"2026-02-03T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.9623,"modality":"semantic_status","timestamp":"2026-02-03T12:00:20Z","metadata":{"arrival_time":"2026-02-03T12:00:40+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-033","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.73,"modality":"semantic_status","timestamp":"2026-02-03T12:00:12Z","metadata":{"arrival_time":"2026-02-03T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-03T12:00:10+00:00","obs-2":"2026-02-03T12:00:20+00:00","obs-distractor":"2026-02-03T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-03T12:00:10+00:00","obs-2":"2026-02-03T12:00:40+00:00","obs-distractor":"2026-02-03T12:00:12+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.958,"edge-ai-1":0.597},"confidence":{"obs-1":0.7831,"obs-2":0.9623,"obs-distractor":0.73},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-033-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8647511140362986,"event_time":"2026-02-03T12:00:20+00:00","arrival_time":"2026-02-03T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.27918200000000004,"normal":0.720818},"reference_distribution":{"anomalous":0.8647511140362986,"normal":0.13524888596370135}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.720818,"event_time":"2026-02-03T12:00:10+00:00","arrival_time":"2026-02-03T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.27918200000000004,"normal":0.720818}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-03T12:00:10+00:00","arrival_time":"2026-02-03T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.720818,"event_time":"2026-02-03T12:00:12+00:00","arrival_time":"2026-02-03T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.27918200000000004,"normal":0.720818},"reference_distribution":{"anomalous":0.27918200000000004,"normal":0.720818}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-03T12:00:12+00:00","arrival_time":"2026-02-03T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8647511140362986,"event_time":"2026-02-03T12:00:20+00:00","arrival_time":"2026-02-03T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.27918200000000004,"normal":0.720818},"reference_distribution":{"anomalous":0.8647511140362986,"normal":0.13524888596370135}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-033-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-03T12:00:20+00:00","arrival_time":"2026-02-03T12:00:40+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":33,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"b4e1630a59476440470434ac732ca1015ad086a07a2496ebde04c5e35121f4db"}}
{"id":"evaluation-v1-justified_revision-20260725-034","name":"Evaluation v1.0 trajectory: justified_revision case 034","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-034","label":"Distractor 034","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7838,"modality":"semantic_status","timestamp":"2026-02-04T12:00:10Z","metadata":{"arrival_time":"2026-02-04T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.962067,"modality":"semantic_status","timestamp":"2026-02-04T12:00:20Z","metadata":{"arrival_time":"2026-02-04T12:00:24+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-034","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.74,"modality":"semantic_status","timestamp":"2026-02-04T12:00:13Z","metadata":{"arrival_time":"2026-02-04T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-04T12:00:10+00:00","obs-2":"2026-02-04T12:00:20+00:00","obs-distractor":"2026-02-04T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-04T12:00:10+00:00","obs-2":"2026-02-04T12:00:24+00:00","obs-distractor":"2026-02-04T12:00:13+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.966,"edge-ai-1":0.608},"confidence":{"obs-1":0.7838,"obs-2":0.962067,"obs-distractor":0.74},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-034-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6506472717445375,"event_time":"2026-02-04T12:00:20+00:00","arrival_time":"2026-02-04T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22584919999999997,"normal":0.7741508},"reference_distribution":{"anomalous":0.6506472717445375,"normal":0.3493527282554625}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7741508,"event_time":"2026-02-04T12:00:10+00:00","arrival_time":"2026-02-04T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.22584919999999997,"normal":0.7741508}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-04T12:00:10+00:00","arrival_time":"2026-02-04T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7741508,"event_time":"2026-02-04T12:00:13+00:00","arrival_time":"2026-02-04T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22584919999999997,"normal":0.7741508},"reference_distribution":{"anomalous":0.22584919999999997,"normal":0.7741508}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-04T12:00:13+00:00","arrival_time":"2026-02-04T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6506472717445375,"event_time":"2026-02-04T12:00:20+00:00","arrival_time":"2026-02-04T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22584919999999997,"normal":0.7741508},"reference_distribution":{"anomalous":0.6506472717445375,"normal":0.3493527282554625}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-034-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-04T12:00:20+00:00","arrival_time":"2026-02-04T12:00:24+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":34,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"ce41a9a7c9d92f5f4d091af07fb6b49c1115a600feb7c6b91479ddb61365ccb1"}}
{"id":"evaluation-v1-justified_revision-20260725-035","name":"Evaluation v1.0 trajectory: justified_revision case 035","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-035","label":"Distractor 035","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7845,"modality":"semantic_status","timestamp":"2026-02-05T12:00:10Z","metadata":{"arrival_time":"2026-02-05T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.961833,"modality":"semantic_status","timestamp":"2026-02-05T12:00:20Z","metadata":{"arrival_time":"2026-02-05T12:00:25+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-035","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.75,"modality":"semantic_status","timestamp":"2026-02-05T12:00:14Z","metadata":{"arrival_time":"2026-02-05T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-05T12:00:10+00:00","obs-2":"2026-02-05T12:00:20+00:00","obs-distractor":"2026-02-05T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-05T12:00:10+00:00","obs-2":"2026-02-05T12:00:25+00:00","obs-distractor":"2026-02-05T12:00:14+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.974,"edge-ai-1":0.619},"confidence":{"obs-1":0.7845,"obs-2":0.961833,"obs-distractor":0.75},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-035-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8766581287712619,"event_time":"2026-02-05T12:00:20+00:00","arrival_time":"2026-02-05T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.272969,"normal":0.727031},"reference_distribution":{"anomalous":0.8766581287712619,"normal":0.12334187122873803}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.727031,"event_time":"2026-02-05T12:00:10+00:00","arrival_time":"2026-02-05T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.272969,"normal":0.727031}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-05T12:00:10+00:00","arrival_time":"2026-02-05T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.727031,"event_time":"2026-02-05T12:00:14+00:00","arrival_time":"2026-02-05T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.272969,"normal":0.727031},"reference_distribution":{"anomalous":0.272969,"normal":0.727031}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-05T12:00:14+00:00","arrival_time":"2026-02-05T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8766581287712619,"event_time":"2026-02-05T12:00:20+00:00","arrival_time":"2026-02-05T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.272969,"normal":0.727031},"reference_distribution":{"anomalous":0.8766581287712619,"normal":0.12334187122873803}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-035-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-05T12:00:20+00:00","arrival_time":"2026-02-05T12:00:25+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":35,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"8d00e70e7656619047f04c3ccd4f1642e382228c938e27fcd591878cef123328"}}
{"id":"evaluation-v1-justified_revision-20260725-036","name":"Evaluation v1.0 trajectory: justified_revision case 036","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-036","label":"Distractor 036","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7852,"modality":"semantic_status","timestamp":"2026-02-06T12:00:10Z","metadata":{"arrival_time":"2026-02-06T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-036","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.76,"modality":"semantic_status","timestamp":"2026-02-06T12:00:12Z","metadata":{"arrival_time":"2026-02-06T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.9616,"modality":"semantic_status","timestamp":"2026-02-06T12:00:20Z","metadata":{"arrival_time":"2026-02-06T12:00:26+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-02-06T12:00:10+00:00","obs-distractor":"2026-02-06T12:00:12+00:00","obs-2":"2026-02-06T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-06T12:00:10+00:00","obs-distractor":"2026-02-06T12:00:12+00:00","obs-2":"2026-02-06T12:00:26+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.91,"edge-ai-1":0.63},"confidence":{"obs-1":0.7852,"obs-distractor":0.76,"obs-2":0.9616},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-036-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.684219526553002,"event_time":"2026-02-06T12:00:20+00:00","arrival_time":"2026-02-06T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2404679999999999,"normal":0.7595320000000001},"reference_distribution":{"anomalous":0.684219526553002,"normal":0.31578047344699794}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7595320000000001,"event_time":"2026-02-06T12:00:10+00:00","arrival_time":"2026-02-06T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2404679999999999,"normal":0.7595320000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-06T12:00:10+00:00","arrival_time":"2026-02-06T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7595320000000001,"event_time":"2026-02-06T12:00:12+00:00","arrival_time":"2026-02-06T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2404679999999999,"normal":0.7595320000000001},"reference_distribution":{"anomalous":0.2404679999999999,"normal":0.7595320000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-06T12:00:12+00:00","arrival_time":"2026-02-06T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.684219526553002,"event_time":"2026-02-06T12:00:20+00:00","arrival_time":"2026-02-06T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2404679999999999,"normal":0.7595320000000001},"reference_distribution":{"anomalous":0.684219526553002,"normal":0.31578047344699794}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-036-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-06T12:00:20+00:00","arrival_time":"2026-02-06T12:00:26+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":36,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"3a2002b15dd4fde6f3af98fdd3073faf257a4a5b0573f738a9b56d913975c185"}}
{"id":"evaluation-v1-justified_revision-20260725-037","name":"Evaluation v1.0 trajectory: justified_revision case 037","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-037","label":"Distractor 037","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7859,"modality":"semantic_status","timestamp":"2026-02-07T12:00:10Z","metadata":{"arrival_time":"2026-02-07T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.961367,"modality":"semantic_status","timestamp":"2026-02-07T12:00:20Z","metadata":{"arrival_time":"2026-02-07T12:00:27+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-037","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.77,"modality":"semantic_status","timestamp":"2026-02-07T12:00:13Z","metadata":{"arrival_time":"2026-02-07T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-07T12:00:10+00:00","obs-2":"2026-02-07T12:00:20+00:00","obs-distractor":"2026-02-07T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-07T12:00:10+00:00","obs-2":"2026-02-07T12:00:27+00:00","obs-distractor":"2026-02-07T12:00:13+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.918,"edge-ai-1":0.641},"confidence":{"obs-1":0.7859,"obs-2":0.961367,"obs-distractor":0.77},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-037-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8145684144666363,"event_time":"2026-02-07T12:00:20+00:00","arrival_time":"2026-02-07T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2667056,"normal":0.7332944},"reference_distribution":{"anomalous":0.8145684144666363,"normal":0.18543158553336375}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7332944,"event_time":"2026-02-07T12:00:10+00:00","arrival_time":"2026-02-07T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2667056,"normal":0.7332944}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-07T12:00:10+00:00","arrival_time":"2026-02-07T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7332944,"event_time":"2026-02-07T12:00:13+00:00","arrival_time":"2026-02-07T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2667056,"normal":0.7332944},"reference_distribution":{"anomalous":0.2667056,"normal":0.7332944}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-07T12:00:13+00:00","arrival_time":"2026-02-07T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8145684144666363,"event_time":"2026-02-07T12:00:20+00:00","arrival_time":"2026-02-07T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2667056,"normal":0.7332944},"reference_distribution":{"anomalous":0.8145684144666363,"normal":0.18543158553336375}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-037-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-07T12:00:20+00:00","arrival_time":"2026-02-07T12:00:27+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":37,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"cba42ff968d7802273f7b08cdf2893a3f6ea1a418d377c9bbe79076ecca1c452"}}
{"id":"evaluation-v1-justified_revision-20260725-038","name":"Evaluation v1.0 trajectory: justified_revision case 038","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-038","label":"Distractor 038","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7866,"modality":"semantic_status","timestamp":"2026-02-08T12:00:10Z","metadata":{"arrival_time":"2026-02-08T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.961133,"modality":"semantic_status","timestamp":"2026-02-08T12:00:20Z","metadata":{"arrival_time":"2026-02-08T12:00:28+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-038","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.78,"modality":"semantic_status","timestamp":"2026-02-08T12:00:14Z","metadata":{"arrival_time":"2026-02-08T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-08T12:00:10+00:00","obs-2":"2026-02-08T12:00:20+00:00","obs-distractor":"2026-02-08T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-08T12:00:10+00:00","obs-2":"2026-02-08T12:00:28+00:00","obs-distractor":"2026-02-08T12:00:14+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.926,"edge-ai-1":0.652},"confidence":{"obs-1":0.7866,"obs-2":0.961133,"obs-distractor":0.78},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-038-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6929789853211877,"event_time":"2026-02-08T12:00:20+00:00","arrival_time":"2026-02-08T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23460839999999994,"normal":0.7653916000000001},"reference_distribution":{"anomalous":0.6929789853211877,"normal":0.3070210146788122}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7653916000000001,"event_time":"2026-02-08T12:00:10+00:00","arrival_time":"2026-02-08T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.23460839999999994,"normal":0.7653916000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-08T12:00:10+00:00","arrival_time":"2026-02-08T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7653916000000001,"event_time":"2026-02-08T12:00:14+00:00","arrival_time":"2026-02-08T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23460839999999994,"normal":0.7653916000000001},"reference_distribution":{"anomalous":0.23460839999999994,"normal":0.7653916000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-08T12:00:14+00:00","arrival_time":"2026-02-08T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6929789853211877,"event_time":"2026-02-08T12:00:20+00:00","arrival_time":"2026-02-08T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23460839999999994,"normal":0.7653916000000001},"reference_distribution":{"anomalous":0.6929789853211877,"normal":0.3070210146788122}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-038-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-08T12:00:20+00:00","arrival_time":"2026-02-08T12:00:28+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":38,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"bb84f555b1ff60541c1199b368e45378691da9bada60b8e68d1a1378ab87cf9e"}}
{"id":"evaluation-v1-justified_revision-20260725-039","name":"Evaluation v1.0 trajectory: justified_revision case 039","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-039","label":"Distractor 039","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7873,"modality":"semantic_status","timestamp":"2026-02-09T12:00:10Z","metadata":{"arrival_time":"2026-02-09T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.9609,"modality":"semantic_status","timestamp":"2026-02-09T12:00:20Z","metadata":{"arrival_time":"2026-02-09T12:00:29+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-039","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.79,"modality":"semantic_status","timestamp":"2026-02-09T12:00:12Z","metadata":{"arrival_time":"2026-02-09T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-09T12:00:10+00:00","obs-2":"2026-02-09T12:00:20+00:00","obs-distractor":"2026-02-09T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-09T12:00:10+00:00","obs-2":"2026-02-09T12:00:29+00:00","obs-distractor":"2026-02-09T12:00:12+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.934,"edge-ai-1":0.52},"confidence":{"obs-1":0.7873,"obs-2":0.9609,"obs-distractor":0.79},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-039-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8249371587424249,"event_time":"2026-02-09T12:00:20+00:00","arrival_time":"2026-02-09T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26039180000000006,"normal":0.7396081999999999},"reference_distribution":{"anomalous":0.8249371587424249,"normal":0.17506284125757515}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7396081999999999,"event_time":"2026-02-09T12:00:10+00:00","arrival_time":"2026-02-09T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.26039180000000006,"normal":0.7396081999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-09T12:00:10+00:00","arrival_time":"2026-02-09T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7396081999999999,"event_time":"2026-02-09T12:00:12+00:00","arrival_time":"2026-02-09T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26039180000000006,"normal":0.7396081999999999},"reference_distribution":{"anomalous":0.26039180000000006,"normal":0.7396081999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-09T12:00:12+00:00","arrival_time":"2026-02-09T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8249371587424249,"event_time":"2026-02-09T12:00:20+00:00","arrival_time":"2026-02-09T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26039180000000006,"normal":0.7396081999999999},"reference_distribution":{"anomalous":0.8249371587424249,"normal":0.17506284125757515}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-039-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-09T12:00:20+00:00","arrival_time":"2026-02-09T12:00:29+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":39,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"cd88c751fe2695cb4e5f8f7cf3492e6e34b860d11137c81d12b873d05728e680"}}
{"id":"evaluation-v1-justified_revision-20260725-040","name":"Evaluation v1.0 trajectory: justified_revision case 040","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-040","label":"Distractor 040","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.788,"modality":"semantic_status","timestamp":"2026-02-10T12:00:10Z","metadata":{"arrival_time":"2026-02-10T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.960667,"modality":"semantic_status","timestamp":"2026-02-10T12:00:20Z","metadata":{"arrival_time":"2026-02-10T12:00:30+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-040","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-02-10T12:00:13Z","metadata":{"arrival_time":"2026-02-10T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-10T12:00:10+00:00","obs-2":"2026-02-10T12:00:20+00:00","obs-distractor":"2026-02-10T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-10T12:00:10+00:00","obs-2":"2026-02-10T12:00:30+00:00","obs-distractor":"2026-02-10T12:00:13+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.942,"edge-ai-1":0.531},"confidence":{"obs-1":0.788,"obs-2":0.960667,"obs-distractor":0.6},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-040-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7023002065094093,"event_time":"2026-02-10T12:00:20+00:00","arrival_time":"2026-02-10T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22870400000000002,"normal":0.771296},"reference_distribution":{"anomalous":0.7023002065094093,"normal":0.2976997934905907}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.771296,"event_time":"2026-02-10T12:00:10+00:00","arrival_time":"2026-02-10T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.22870400000000002,"normal":0.771296}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-10T12:00:10+00:00","arrival_time":"2026-02-10T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.771296,"event_time":"2026-02-10T12:00:13+00:00","arrival_time":"2026-02-10T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22870400000000002,"normal":0.771296},"reference_distribution":{"anomalous":0.22870400000000002,"normal":0.771296}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-10T12:00:13+00:00","arrival_time":"2026-02-10T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7023002065094093,"event_time":"2026-02-10T12:00:20+00:00","arrival_time":"2026-02-10T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22870400000000002,"normal":0.771296},"reference_distribution":{"anomalous":0.7023002065094093,"normal":0.2976997934905907}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-040-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-10T12:00:20+00:00","arrival_time":"2026-02-10T12:00:30+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":40,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"01c64adb82a985176ebe1c3ca396dd41ff708492e2b9f3b7d8216c882fe3870f"}}
{"id":"evaluation-v1-justified_revision-20260725-041","name":"Evaluation v1.0 trajectory: justified_revision case 041","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-041","label":"Distractor 041","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7887,"modality":"semantic_status","timestamp":"2026-02-11T12:00:10Z","metadata":{"arrival_time":"2026-02-11T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-041","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-02-11T12:00:14Z","metadata":{"arrival_time":"2026-02-11T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.960433,"modality":"semantic_status","timestamp":"2026-02-11T12:00:20Z","metadata":{"arrival_time":"2026-02-11T12:00:31+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-11T12:00:10+00:00","obs-distractor":"2026-02-11T12:00:14+00:00","obs-2":"2026-02-11T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-11T12:00:10+00:00","obs-distractor":"2026-02-11T12:00:14+00:00","obs-2":"2026-02-11T12:00:31+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.95,"edge-ai-1":0.542},"confidence":{"obs-1":0.7887,"obs-distractor":0.61,"obs-2":0.960433},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-041-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8360727038066142,"event_time":"2026-02-11T12:00:20+00:00","arrival_time":"2026-02-11T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2540276,"normal":0.7459724},"reference_distribution":{"anomalous":0.8360727038066142,"normal":0.16392729619338567}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7459724,"event_time":"2026-02-11T12:00:10+00:00","arrival_time":"2026-02-11T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2540276,"normal":0.7459724}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-11T12:00:10+00:00","arrival_time":"2026-02-11T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7459724,"event_time":"2026-02-11T12:00:14+00:00","arrival_time":"2026-02-11T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2540276,"normal":0.7459724},"reference_distribution":{"anomalous":0.2540276,"normal":0.7459724}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-11T12:00:14+00:00","arrival_time":"2026-02-11T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8360727038066142,"event_time":"2026-02-11T12:00:20+00:00","arrival_time":"2026-02-11T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2540276,"normal":0.7459724},"reference_distribution":{"anomalous":0.8360727038066142,"normal":0.16392729619338567}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-041-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-11T12:00:20+00:00","arrival_time":"2026-02-11T12:00:31+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":41,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"788de78422e1ecd20184b51e44d8b3db1f936d95b84298bc20397e9a5704832f"}}
{"id":"evaluation-v1-justified_revision-20260725-042","name":"Evaluation v1.0 trajectory: justified_revision case 042","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-042","label":"Distractor 042","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7894,"modality":"semantic_status","timestamp":"2026-02-12T12:00:10Z","metadata":{"arrival_time":"2026-02-12T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.9602,"modality":"semantic_status","timestamp":"2026-02-12T12:00:20Z","metadata":{"arrival_time":"2026-02-12T12:00:32+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-042","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-02-12T12:00:12Z","metadata":{"arrival_time":"2026-02-12T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-12T12:00:10+00:00","obs-2":"2026-02-12T12:00:20+00:00","obs-distractor":"2026-02-12T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-12T12:00:10+00:00","obs-2":"2026-02-12T12:00:32+00:00","obs-distractor":"2026-02-12T12:00:12+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.958,"edge-ai-1":0.553},"confidence":{"obs-1":0.7894,"obs-2":0.9602,"obs-distractor":0.62},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-042-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7122546393044682,"event_time":"2026-02-12T12:00:20+00:00","arrival_time":"2026-02-12T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22275480000000003,"normal":0.7772452},"reference_distribution":{"anomalous":0.7122546393044682,"normal":0.28774536069553175}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7772452,"event_time":"2026-02-12T12:00:10+00:00","arrival_time":"2026-02-12T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.22275480000000003,"normal":0.7772452}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-12T12:00:10+00:00","arrival_time":"2026-02-12T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7772452,"event_time":"2026-02-12T12:00:12+00:00","arrival_time":"2026-02-12T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22275480000000003,"normal":0.7772452},"reference_distribution":{"anomalous":0.22275480000000003,"normal":0.7772452}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-12T12:00:12+00:00","arrival_time":"2026-02-12T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.7122546393044682,"event_time":"2026-02-12T12:00:20+00:00","arrival_time":"2026-02-12T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22275480000000003,"normal":0.7772452},"reference_distribution":{"anomalous":0.7122546393044682,"normal":0.28774536069553175}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-042-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-12T12:00:20+00:00","arrival_time":"2026-02-12T12:00:32+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":42,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"77b9a8f2e56561bc01c64b39743d08e57ebc8339f3a008cd1896908cb8b21dba"}}
{"id":"evaluation-v1-justified_revision-20260725-043","name":"Evaluation v1.0 trajectory: justified_revision case 043","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-043","label":"Distractor 043","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7901,"modality":"semantic_status","timestamp":"2026-02-13T12:00:10Z","metadata":{"arrival_time":"2026-02-13T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.959967,"modality":"semantic_status","timestamp":"2026-02-13T12:00:20Z","metadata":{"arrival_time":"2026-02-13T12:00:33+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-043","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-02-13T12:00:13Z","metadata":{"arrival_time":"2026-02-13T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-13T12:00:10+00:00","obs-2":"2026-02-13T12:00:20+00:00","obs-distractor":"2026-02-13T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-13T12:00:10+00:00","obs-2":"2026-02-13T12:00:33+00:00","obs-distractor":"2026-02-13T12:00:13+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.966,"edge-ai-1":0.564},"confidence":{"obs-1":0.7901,"obs-2":0.959967,"obs-distractor":0.63},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-043-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8480792110135235,"event_time":"2026-02-13T12:00:20+00:00","arrival_time":"2026-02-13T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24761299999999997,"normal":0.752387},"reference_distribution":{"anomalous":0.8480792110135235,"normal":0.15192078898647657}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.752387,"event_time":"2026-02-13T12:00:10+00:00","arrival_time":"2026-02-13T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.24761299999999997,"normal":0.752387}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-13T12:00:10+00:00","arrival_time":"2026-02-13T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.752387,"event_time":"2026-02-13T12:00:13+00:00","arrival_time":"2026-02-13T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24761299999999997,"normal":0.752387},"reference_distribution":{"anomalous":0.24761299999999997,"normal":0.752387}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-13T12:00:13+00:00","arrival_time":"2026-02-13T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8480792110135235,"event_time":"2026-02-13T12:00:20+00:00","arrival_time":"2026-02-13T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24761299999999997,"normal":0.752387},"reference_distribution":{"anomalous":0.8480792110135235,"normal":0.15192078898647657}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-043-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-13T12:00:20+00:00","arrival_time":"2026-02-13T12:00:33+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":43,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c673ea868492e2e9085c4a3607c25d2c36cc6a31e4b496837aed575c5a94a14d"}}
{"id":"evaluation-v1-justified_revision-20260725-044","name":"Evaluation v1.0 trajectory: justified_revision case 044","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-044","label":"Distractor 044","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7908,"modality":"semantic_status","timestamp":"2026-02-14T12:00:10Z","metadata":{"arrival_time":"2026-02-14T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-044","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-02-14T12:00:14Z","metadata":{"arrival_time":"2026-02-14T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.959733,"modality":"semantic_status","timestamp":"2026-02-14T12:00:20Z","metadata":{"arrival_time":"2026-02-14T12:00:34+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-02-14T12:00:10+00:00","obs-distractor":"2026-02-14T12:00:14+00:00","obs-2":"2026-02-14T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-14T12:00:10+00:00","obs-distractor":"2026-02-14T12:00:14+00:00","obs-2":"2026-02-14T12:00:34+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.974,"edge-ai-1":0.575},"confidence":{"obs-1":0.7908,"obs-distractor":0.64,"obs-2":0.959733},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-044-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.626913591655002,"event_time":"2026-02-14T12:00:20+00:00","arrival_time":"2026-02-14T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2167608000000001,"normal":0.7832391999999999},"reference_distribution":{"anomalous":0.626913591655002,"normal":0.373086408344998}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7832391999999999,"event_time":"2026-02-14T12:00:10+00:00","arrival_time":"2026-02-14T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2167608000000001,"normal":0.7832391999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-14T12:00:10+00:00","arrival_time":"2026-02-14T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7832391999999999,"event_time":"2026-02-14T12:00:14+00:00","arrival_time":"2026-02-14T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2167608000000001,"normal":0.7832391999999999},"reference_distribution":{"anomalous":0.2167608000000001,"normal":0.7832391999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-14T12:00:14+00:00","arrival_time":"2026-02-14T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.626913591655002,"event_time":"2026-02-14T12:00:20+00:00","arrival_time":"2026-02-14T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2167608000000001,"normal":0.7832391999999999},"reference_distribution":{"anomalous":0.626913591655002,"normal":0.373086408344998}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-044-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-14T12:00:20+00:00","arrival_time":"2026-02-14T12:00:34+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":44,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"a09de77bba30c018914729621d07a8268f339f02031e9e7ecc80a683fa2724cc"}}
{"id":"evaluation-v1-justified_revision-20260725-045","name":"Evaluation v1.0 trajectory: justified_revision case 045","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-045","label":"Distractor 045","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7915,"modality":"semantic_status","timestamp":"2026-02-15T12:00:10Z","metadata":{"arrival_time":"2026-02-15T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.9595,"modality":"semantic_status","timestamp":"2026-02-15T12:00:20Z","metadata":{"arrival_time":"2026-02-15T12:00:35+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-045","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-02-15T12:00:12Z","metadata":{"arrival_time":"2026-02-15T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-15T12:00:10+00:00","obs-2":"2026-02-15T12:00:20+00:00","obs-distractor":"2026-02-15T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-15T12:00:10+00:00","obs-2":"2026-02-15T12:00:35+00:00","obs-distractor":"2026-02-15T12:00:12+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.91,"edge-ai-1":0.586},"confidence":{"obs-1":0.7915,"obs-2":0.9595,"obs-distractor":0.65},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-045-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.805779550609493,"event_time":"2026-02-15T12:00:20+00:00","arrival_time":"2026-02-15T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.27000650000000004,"normal":0.7299935},"reference_distribution":{"anomalous":0.805779550609493,"normal":0.19422044939050698}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7299935,"event_time":"2026-02-15T12:00:10+00:00","arrival_time":"2026-02-15T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.27000650000000004,"normal":0.7299935}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-15T12:00:10+00:00","arrival_time":"2026-02-15T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7299935,"event_time":"2026-02-15T12:00:12+00:00","arrival_time":"2026-02-15T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.27000650000000004,"normal":0.7299935},"reference_distribution":{"anomalous":0.27000650000000004,"normal":0.7299935}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-15T12:00:12+00:00","arrival_time":"2026-02-15T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.805779550609493,"event_time":"2026-02-15T12:00:20+00:00","arrival_time":"2026-02-15T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.27000650000000004,"normal":0.7299935},"reference_distribution":{"anomalous":0.805779550609493,"normal":0.19422044939050698}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-045-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-15T12:00:20+00:00","arrival_time":"2026-02-15T12:00:35+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":45,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"69fadf1c1ee5e1f1b285f4ec136c0d0a2f74f4650af012b4df94053702fca6fe"}}
{"id":"evaluation-v1-justified_revision-20260725-046","name":"Evaluation v1.0 trajectory: justified_revision case 046","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-046","label":"Distractor 046","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7922,"modality":"semantic_status","timestamp":"2026-02-16T12:00:10Z","metadata":{"arrival_time":"2026-02-16T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-046","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-02-16T12:00:13Z","metadata":{"arrival_time":"2026-02-16T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.959267,"modality":"semantic_status","timestamp":"2026-02-16T12:00:20Z","metadata":{"arrival_time":"2026-02-16T12:00:36+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-02-16T12:00:10+00:00","obs-distractor":"2026-02-16T12:00:13+00:00","obs-2":"2026-02-16T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-16T12:00:10+00:00","obs-distractor":"2026-02-16T12:00:13+00:00","obs-2":"2026-02-16T12:00:36+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.918,"edge-ai-1":0.597},"confidence":{"obs-1":0.7922,"obs-distractor":0.66,"obs-2":0.959267},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-046-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6619330342531898,"event_time":"2026-02-16T12:00:20+00:00","arrival_time":"2026-02-16T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23176039999999998,"normal":0.7682396},"reference_distribution":{"anomalous":0.6619330342531898,"normal":0.33806696574681017}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7682396,"event_time":"2026-02-16T12:00:10+00:00","arrival_time":"2026-02-16T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.23176039999999998,"normal":0.7682396}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-16T12:00:10+00:00","arrival_time":"2026-02-16T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7682396,"event_time":"2026-02-16T12:00:13+00:00","arrival_time":"2026-02-16T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23176039999999998,"normal":0.7682396},"reference_distribution":{"anomalous":0.23176039999999998,"normal":0.7682396}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-16T12:00:13+00:00","arrival_time":"2026-02-16T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6619330342531898,"event_time":"2026-02-16T12:00:20+00:00","arrival_time":"2026-02-16T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23176039999999998,"normal":0.7682396},"reference_distribution":{"anomalous":0.6619330342531898,"normal":0.33806696574681017}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-046-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-16T12:00:20+00:00","arrival_time":"2026-02-16T12:00:36+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":46,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"89a2e7f7aa71746c1f1d4b03aede9cf6c7b1ff9a04b9891cf75e045fc17d71d7"}}
{"id":"evaluation-v1-justified_revision-20260725-047","name":"Evaluation v1.0 trajectory: justified_revision case 047","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-047","label":"Distractor 047","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7929,"modality":"semantic_status","timestamp":"2026-02-17T12:00:10Z","metadata":{"arrival_time":"2026-02-17T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-047","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-02-17T12:00:14Z","metadata":{"arrival_time":"2026-02-17T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.959033,"modality":"semantic_status","timestamp":"2026-02-17T12:00:20Z","metadata":{"arrival_time":"2026-02-17T12:00:37+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-17T12:00:10+00:00","obs-distractor":"2026-02-17T12:00:14+00:00","obs-2":"2026-02-17T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-17T12:00:10+00:00","obs-distractor":"2026-02-17T12:00:14+00:00","obs-2":"2026-02-17T12:00:37+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.926,"edge-ai-1":0.608},"confidence":{"obs-1":0.7929,"obs-distractor":0.67,"obs-2":0.959033},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-047-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8154844944975129,"event_time":"2026-02-17T12:00:20+00:00","arrival_time":"2026-02-17T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26362969999999997,"normal":0.7363703},"reference_distribution":{"anomalous":0.8154844944975129,"normal":0.1845155055024871}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7363703,"event_time":"2026-02-17T12:00:10+00:00","arrival_time":"2026-02-17T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.26362969999999997,"normal":0.7363703}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-17T12:00:10+00:00","arrival_time":"2026-02-17T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7363703,"event_time":"2026-02-17T12:00:14+00:00","arrival_time":"2026-02-17T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26362969999999997,"normal":0.7363703},"reference_distribution":{"anomalous":0.26362969999999997,"normal":0.7363703}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-17T12:00:14+00:00","arrival_time":"2026-02-17T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8154844944975129,"event_time":"2026-02-17T12:00:20+00:00","arrival_time":"2026-02-17T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.26362969999999997,"normal":0.7363703},"reference_distribution":{"anomalous":0.8154844944975129,"normal":0.1845155055024871}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-047-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-17T12:00:20+00:00","arrival_time":"2026-02-17T12:00:37+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":47,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"90e685477b09e2f913402cd943bdfa4facdfa3acaa9afc4f881e3f259228273c"}}
{"id":"evaluation-v1-justified_revision-20260725-048","name":"Evaluation v1.0 trajectory: justified_revision case 048","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-048","label":"Distractor 048","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7936,"modality":"semantic_status","timestamp":"2026-02-18T12:00:10Z","metadata":{"arrival_time":"2026-02-18T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-048","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-02-18T12:00:12Z","metadata":{"arrival_time":"2026-02-18T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.9588,"modality":"semantic_status","timestamp":"2026-02-18T12:00:20Z","metadata":{"arrival_time":"2026-02-18T12:00:38+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-02-18T12:00:10+00:00","obs-distractor":"2026-02-18T12:00:12+00:00","obs-2":"2026-02-18T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-18T12:00:10+00:00","obs-distractor":"2026-02-18T12:00:12+00:00","obs-2":"2026-02-18T12:00:38+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.934,"edge-ai-1":0.619},"confidence":{"obs-1":0.7936,"obs-distractor":0.68,"obs-2":0.9588},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-048-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6699485005281088,"event_time":"2026-02-18T12:00:20+00:00","arrival_time":"2026-02-18T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22577760000000002,"normal":0.7742224},"reference_distribution":{"anomalous":0.6699485005281088,"normal":0.3300514994718911}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7742224,"event_time":"2026-02-18T12:00:10+00:00","arrival_time":"2026-02-18T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.22577760000000002,"normal":0.7742224}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-18T12:00:10+00:00","arrival_time":"2026-02-18T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7742224,"event_time":"2026-02-18T12:00:12+00:00","arrival_time":"2026-02-18T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22577760000000002,"normal":0.7742224},"reference_distribution":{"anomalous":0.22577760000000002,"normal":0.7742224}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-18T12:00:12+00:00","arrival_time":"2026-02-18T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"robot-1","reference_confidence":0.6699485005281088,"event_time":"2026-02-18T12:00:20+00:00","arrival_time":"2026-02-18T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22577760000000002,"normal":0.7742224},"reference_distribution":{"anomalous":0.6699485005281088,"normal":0.3300514994718911}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-048-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-18T12:00:20+00:00","arrival_time":"2026-02-18T12:00:38+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":48,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"7479e2eccd25c923ac4c63aed98447b613e4d2456d7b035f86b244e1a3d96334"}}
{"id":"evaluation-v1-justified_revision-20260725-049","name":"Evaluation v1.0 trajectory: justified_revision case 049","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-049","label":"Distractor 049","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.7943,"modality":"semantic_status","timestamp":"2026-02-19T12:00:10Z","metadata":{"arrival_time":"2026-02-19T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.958567,"modality":"semantic_status","timestamp":"2026-02-19T12:00:20Z","metadata":{"arrival_time":"2026-02-19T12:00:39+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-049","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-02-19T12:00:13Z","metadata":{"arrival_time":"2026-02-19T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-19T12:00:10+00:00","obs-2":"2026-02-19T12:00:20+00:00","obs-distractor":"2026-02-19T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-19T12:00:10+00:00","obs-2":"2026-02-19T12:00:39+00:00","obs-distractor":"2026-02-19T12:00:13+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.942,"edge-ai-1":0.63},"confidence":{"obs-1":0.7943,"obs-2":0.958567,"obs-distractor":0.69},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-049-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8258928152447704,"event_time":"2026-02-19T12:00:20+00:00","arrival_time":"2026-02-19T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2572025,"normal":0.7427975},"reference_distribution":{"anomalous":0.8258928152447704,"normal":0.17410718475522957}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7427975,"event_time":"2026-02-19T12:00:10+00:00","arrival_time":"2026-02-19T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2572025,"normal":0.7427975}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-19T12:00:10+00:00","arrival_time":"2026-02-19T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7427975,"event_time":"2026-02-19T12:00:13+00:00","arrival_time":"2026-02-19T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2572025,"normal":0.7427975},"reference_distribution":{"anomalous":0.2572025,"normal":0.7427975}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-19T12:00:13+00:00","arrival_time":"2026-02-19T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.8258928152447704,"event_time":"2026-02-19T12:00:20+00:00","arrival_time":"2026-02-19T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2572025,"normal":0.7427975},"reference_distribution":{"anomalous":0.8258928152447704,"normal":0.17410718475522957}}],"contradictions":[{"contradiction_id":"evaluation-v1-justified_revision-20260725-049-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-19T12:00:20+00:00","arrival_time":"2026-02-19T12:00:39+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"justified_revision","case_index":49,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"67f7fdf6b9e167664c4e9f544af98212b16b102aca30f41d10d3daa85aa1aee1"}}
{"id":"evaluation-v1-belief_preservation-20260725-000","name":"Evaluation v1.0 trajectory: belief_preservation case 000","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-000","label":"Distractor 000","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.93,"modality":"semantic_status","timestamp":"2026-01-01T12:00:10Z","metadata":{"arrival_time":"2026-01-01T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-000","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-01-01T12:00:12Z","metadata":{"arrival_time":"2026-01-01T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53,"modality":"semantic_status","timestamp":"2026-01-01T12:00:20Z","metadata":{"arrival_time":"2026-01-01T12:00:24+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-01-01T12:00:10+00:00","obs-distractor":"2026-01-01T12:00:12+00:00","obs-2":"2026-01-01T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-01T12:00:10+00:00","obs-distractor":"2026-01-01T12:00:12+00:00","obs-2":"2026-01-01T12:00:24+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.91,"edge-ai-1":0.52},"confidence":{"obs-1":0.93,"obs-distractor":0.6,"obs-2":0.53},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-000-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8851031088204417,"event_time":"2026-01-01T12:00:20+00:00","arrival_time":"2026-01-01T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10870000000000002,"normal":0.8913},"reference_distribution":{"anomalous":0.11489689117955826,"normal":0.8851031088204417}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8913,"event_time":"2026-01-01T12:00:10+00:00","arrival_time":"2026-01-01T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10870000000000002,"normal":0.8913}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-01T12:00:10+00:00","arrival_time":"2026-01-01T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8913,"event_time":"2026-01-01T12:00:12+00:00","arrival_time":"2026-01-01T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10870000000000002,"normal":0.8913},"reference_distribution":{"anomalous":0.10870000000000002,"normal":0.8913}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-01T12:00:12+00:00","arrival_time":"2026-01-01T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8851031088204417,"event_time":"2026-01-01T12:00:20+00:00","arrival_time":"2026-01-01T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10870000000000002,"normal":0.8913},"reference_distribution":{"anomalous":0.11489689117955826,"normal":0.8851031088204417}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-000-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-01T12:00:20+00:00","arrival_time":"2026-01-01T12:00:24+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":0,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"a81facd4ec196e864f95fd97b5ff6f6d8c56a7b7e8dd578dd0b22ce9e44d9713"}}
{"id":"evaluation-v1-belief_preservation-20260725-001","name":"Evaluation v1.0 trajectory: belief_preservation case 001","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-001","label":"Distractor 001","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.929825,"modality":"semantic_status","timestamp":"2026-01-02T12:00:10Z","metadata":{"arrival_time":"2026-01-02T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-001","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-01-02T12:00:13Z","metadata":{"arrival_time":"2026-01-02T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53014,"modality":"semantic_status","timestamp":"2026-01-02T12:00:20Z","metadata":{"arrival_time":"2026-01-02T12:00:25+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-01-02T12:00:10+00:00","obs-distractor":"2026-01-02T12:00:13+00:00","obs-2":"2026-01-02T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-02T12:00:10+00:00","obs-distractor":"2026-01-02T12:00:13+00:00","obs-2":"2026-01-02T12:00:25+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.918,"edge-ai-1":0.531},"confidence":{"obs-1":0.929825,"obs-distractor":0.61,"obs-2":0.53014},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-001-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8302984740451468,"event_time":"2026-01-02T12:00:20+00:00","arrival_time":"2026-01-02T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.160868075,"normal":0.839131925},"reference_distribution":{"anomalous":0.16970152595485322,"normal":0.8302984740451468}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.839131925,"event_time":"2026-01-02T12:00:10+00:00","arrival_time":"2026-01-02T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.160868075,"normal":0.839131925}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-02T12:00:10+00:00","arrival_time":"2026-01-02T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.839131925,"event_time":"2026-01-02T12:00:13+00:00","arrival_time":"2026-01-02T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.160868075,"normal":0.839131925},"reference_distribution":{"anomalous":0.160868075,"normal":0.839131925}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-02T12:00:13+00:00","arrival_time":"2026-01-02T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8302984740451468,"event_time":"2026-01-02T12:00:20+00:00","arrival_time":"2026-01-02T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.160868075,"normal":0.839131925},"reference_distribution":{"anomalous":0.16970152595485322,"normal":0.8302984740451468}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-001-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-02T12:00:20+00:00","arrival_time":"2026-01-02T12:00:25+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":1,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"bb1382378b002a91b2e08702155ee6e030fc9922b58623d41c4cc8061b707cb9"}}
{"id":"evaluation-v1-belief_preservation-20260725-002","name":"Evaluation v1.0 trajectory: belief_preservation case 002","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-002","label":"Distractor 002","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.92965,"modality":"semantic_status","timestamp":"2026-01-03T12:00:10Z","metadata":{"arrival_time":"2026-01-03T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53028,"modality":"semantic_status","timestamp":"2026-01-03T12:00:20Z","metadata":{"arrival_time":"2026-01-03T12:00:26+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-002","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-01-03T12:00:14Z","metadata":{"arrival_time":"2026-01-03T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-03T12:00:10+00:00","obs-2":"2026-01-03T12:00:20+00:00","obs-distractor":"2026-01-03T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-03T12:00:10+00:00","obs-2":"2026-01-03T12:00:26+00:00","obs-distractor":"2026-01-03T12:00:14+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.926,"edge-ai-1":0.542},"confidence":{"obs-1":0.92965,"obs-2":0.53028,"obs-distractor":0.62},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-002-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8916739033629175,"event_time":"2026-01-03T12:00:20+00:00","arrival_time":"2026-01-03T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10214410000000007,"normal":0.8978558999999999},"reference_distribution":{"anomalous":0.10832609663708248,"normal":0.8916739033629175}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8978558999999999,"event_time":"2026-01-03T12:00:10+00:00","arrival_time":"2026-01-03T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10214410000000007,"normal":0.8978558999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-03T12:00:10+00:00","arrival_time":"2026-01-03T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8978558999999999,"event_time":"2026-01-03T12:00:14+00:00","arrival_time":"2026-01-03T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10214410000000007,"normal":0.8978558999999999},"reference_distribution":{"anomalous":0.10214410000000007,"normal":0.8978558999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-03T12:00:14+00:00","arrival_time":"2026-01-03T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8916739033629175,"event_time":"2026-01-03T12:00:20+00:00","arrival_time":"2026-01-03T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10214410000000007,"normal":0.8978558999999999},"reference_distribution":{"anomalous":0.10832609663708248,"normal":0.8916739033629175}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-002-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-03T12:00:20+00:00","arrival_time":"2026-01-03T12:00:26+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":2,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"ff28c3d89b460909b6434d03df73d052748407c257da7ed375f82578d2a98e08"}}
{"id":"evaluation-v1-belief_preservation-20260725-003","name":"Evaluation v1.0 trajectory: belief_preservation case 003","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-003","label":"Distractor 003","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.929475,"modality":"semantic_status","timestamp":"2026-01-04T12:00:10Z","metadata":{"arrival_time":"2026-01-04T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-003","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-01-04T12:00:12Z","metadata":{"arrival_time":"2026-01-04T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53042,"modality":"semantic_status","timestamp":"2026-01-04T12:00:20Z","metadata":{"arrival_time":"2026-01-04T12:00:27+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-01-04T12:00:10+00:00","obs-distractor":"2026-01-04T12:00:12+00:00","obs-2":"2026-01-04T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-04T12:00:10+00:00","obs-distractor":"2026-01-04T12:00:12+00:00","obs-2":"2026-01-04T12:00:27+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.934,"edge-ai-1":0.553},"confidence":{"obs-1":0.929475,"obs-distractor":0.63,"obs-2":0.53042},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-003-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8376382830801247,"event_time":"2026-01-04T12:00:20+00:00","arrival_time":"2026-01-04T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15341367499999992,"normal":0.8465863250000001},"reference_distribution":{"anomalous":0.1623617169198753,"normal":0.8376382830801247}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8465863250000001,"event_time":"2026-01-04T12:00:10+00:00","arrival_time":"2026-01-04T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.15341367499999992,"normal":0.8465863250000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-04T12:00:10+00:00","arrival_time":"2026-01-04T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8465863250000001,"event_time":"2026-01-04T12:00:12+00:00","arrival_time":"2026-01-04T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15341367499999992,"normal":0.8465863250000001},"reference_distribution":{"anomalous":0.15341367499999992,"normal":0.8465863250000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-04T12:00:12+00:00","arrival_time":"2026-01-04T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8376382830801247,"event_time":"2026-01-04T12:00:20+00:00","arrival_time":"2026-01-04T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15341367499999992,"normal":0.8465863250000001},"reference_distribution":{"anomalous":0.1623617169198753,"normal":0.8376382830801247}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-003-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-04T12:00:20+00:00","arrival_time":"2026-01-04T12:00:27+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":3,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"63d62070e9d3efd61376efb1c728208198bcbc32845086b5e113e817c0b59cb2"}}
{"id":"evaluation-v1-belief_preservation-20260725-004","name":"Evaluation v1.0 trajectory: belief_preservation case 004","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-004","label":"Distractor 004","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9293,"modality":"semantic_status","timestamp":"2026-01-05T12:00:10Z","metadata":{"arrival_time":"2026-01-05T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53056,"modality":"semantic_status","timestamp":"2026-01-05T12:00:20Z","metadata":{"arrival_time":"2026-01-05T12:00:28+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-004","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-01-05T12:00:13Z","metadata":{"arrival_time":"2026-01-05T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-05T12:00:10+00:00","obs-2":"2026-01-05T12:00:20+00:00","obs-distractor":"2026-01-05T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-05T12:00:10+00:00","obs-2":"2026-01-05T12:00:28+00:00","obs-distractor":"2026-01-05T12:00:13+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.942,"edge-ai-1":0.564},"confidence":{"obs-1":0.9293,"obs-2":0.53056,"obs-distractor":0.64},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-004-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8982687869661913,"event_time":"2026-01-05T12:00:20+00:00","arrival_time":"2026-01-05T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.0955994,"normal":0.9044006},"reference_distribution":{"anomalous":0.10173121303380868,"normal":0.8982687869661913}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9044006,"event_time":"2026-01-05T12:00:10+00:00","arrival_time":"2026-01-05T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.0955994,"normal":0.9044006}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-05T12:00:10+00:00","arrival_time":"2026-01-05T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.9044006,"event_time":"2026-01-05T12:00:13+00:00","arrival_time":"2026-01-05T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.0955994,"normal":0.9044006},"reference_distribution":{"anomalous":0.0955994,"normal":0.9044006}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-05T12:00:13+00:00","arrival_time":"2026-01-05T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8982687869661913,"event_time":"2026-01-05T12:00:20+00:00","arrival_time":"2026-01-05T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.0955994,"normal":0.9044006},"reference_distribution":{"anomalous":0.10173121303380868,"normal":0.8982687869661913}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-004-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-05T12:00:20+00:00","arrival_time":"2026-01-05T12:00:28+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":4,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"7d0e283f8db9cb79b1b8b4577a959938b39d203d29a72f7d44a4124794261196"}}
{"id":"evaluation-v1-belief_preservation-20260725-005","name":"Evaluation v1.0 trajectory: belief_preservation case 005","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-005","label":"Distractor 005","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.929125,"modality":"semantic_status","timestamp":"2026-01-06T12:00:10Z","metadata":{"arrival_time":"2026-01-06T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-005","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-01-06T12:00:14Z","metadata":{"arrival_time":"2026-01-06T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.5307,"modality":"semantic_status","timestamp":"2026-01-06T12:00:20Z","metadata":{"arrival_time":"2026-01-06T12:00:29+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-01-06T12:00:10+00:00","obs-distractor":"2026-01-06T12:00:14+00:00","obs-2":"2026-01-06T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-06T12:00:10+00:00","obs-distractor":"2026-01-06T12:00:14+00:00","obs-2":"2026-01-06T12:00:29+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.95,"edge-ai-1":0.575},"confidence":{"obs-1":0.929125,"obs-distractor":0.65,"obs-2":0.5307},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-005-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8449999071157424,"event_time":"2026-01-06T12:00:20+00:00","arrival_time":"2026-01-06T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.14597187500000008,"normal":0.8540281249999999},"reference_distribution":{"anomalous":0.1550000928842576,"normal":0.8449999071157424}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8540281249999999,"event_time":"2026-01-06T12:00:10+00:00","arrival_time":"2026-01-06T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.14597187500000008,"normal":0.8540281249999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-06T12:00:10+00:00","arrival_time":"2026-01-06T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8540281249999999,"event_time":"2026-01-06T12:00:14+00:00","arrival_time":"2026-01-06T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.14597187500000008,"normal":0.8540281249999999},"reference_distribution":{"anomalous":0.14597187500000008,"normal":0.8540281249999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-06T12:00:14+00:00","arrival_time":"2026-01-06T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8449999071157424,"event_time":"2026-01-06T12:00:20+00:00","arrival_time":"2026-01-06T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.14597187500000008,"normal":0.8540281249999999},"reference_distribution":{"anomalous":0.1550000928842576,"normal":0.8449999071157424}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-005-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-06T12:00:20+00:00","arrival_time":"2026-01-06T12:00:29+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":5,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"bbffc3c09b3a4185541da8f5902e770da3690ebc4c6f9c2845c7d1f6f955557a"}}
{"id":"evaluation-v1-belief_preservation-20260725-006","name":"Evaluation v1.0 trajectory: belief_preservation case 006","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-006","label":"Distractor 006","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.92895,"modality":"semantic_status","timestamp":"2026-01-07T12:00:10Z","metadata":{"arrival_time":"2026-01-07T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53084,"modality":"semantic_status","timestamp":"2026-01-07T12:00:20Z","metadata":{"arrival_time":"2026-01-07T12:00:30+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-006","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-01-07T12:00:12Z","metadata":{"arrival_time":"2026-01-07T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-07T12:00:10+00:00","obs-2":"2026-01-07T12:00:20+00:00","obs-distractor":"2026-01-07T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-07T12:00:10+00:00","obs-2":"2026-01-07T12:00:30+00:00","obs-distractor":"2026-01-07T12:00:12+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.958,"edge-ai-1":0.586},"confidence":{"obs-1":0.92895,"obs-2":0.53084,"obs-distractor":0.66},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-006-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.9048895071810644,"event_time":"2026-01-07T12:00:20+00:00","arrival_time":"2026-01-07T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.08906590000000003,"normal":0.9109341},"reference_distribution":{"anomalous":0.09511049281893554,"normal":0.9048895071810644}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9109341,"event_time":"2026-01-07T12:00:10+00:00","arrival_time":"2026-01-07T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.08906590000000003,"normal":0.9109341}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-07T12:00:10+00:00","arrival_time":"2026-01-07T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.9109341,"event_time":"2026-01-07T12:00:12+00:00","arrival_time":"2026-01-07T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.08906590000000003,"normal":0.9109341},"reference_distribution":{"anomalous":0.08906590000000003,"normal":0.9109341}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-07T12:00:12+00:00","arrival_time":"2026-01-07T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.9048895071810644,"event_time":"2026-01-07T12:00:20+00:00","arrival_time":"2026-01-07T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.08906590000000003,"normal":0.9109341},"reference_distribution":{"anomalous":0.09511049281893554,"normal":0.9048895071810644}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-006-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-07T12:00:20+00:00","arrival_time":"2026-01-07T12:00:30+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":6,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"d42e399dfb451320a2f41b91ff92c52942482e7063e0f28acde716cde60dbc41"}}
{"id":"evaluation-v1-belief_preservation-20260725-007","name":"Evaluation v1.0 trajectory: belief_preservation case 007","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-007","label":"Distractor 007","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.928775,"modality":"semantic_status","timestamp":"2026-01-08T12:00:10Z","metadata":{"arrival_time":"2026-01-08T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-007","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-01-08T12:00:13Z","metadata":{"arrival_time":"2026-01-08T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53098,"modality":"semantic_status","timestamp":"2026-01-08T12:00:20Z","metadata":{"arrival_time":"2026-01-08T12:00:31+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-01-08T12:00:10+00:00","obs-distractor":"2026-01-08T12:00:13+00:00","obs-2":"2026-01-08T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-08T12:00:10+00:00","obs-distractor":"2026-01-08T12:00:13+00:00","obs-2":"2026-01-08T12:00:31+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.966,"edge-ai-1":0.597},"confidence":{"obs-1":0.928775,"obs-distractor":0.67,"obs-2":0.53098},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-007-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.852385294317571,"event_time":"2026-01-08T12:00:20+00:00","arrival_time":"2026-01-08T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.13854267500000006,"normal":0.8614573249999999},"reference_distribution":{"anomalous":0.147614705682429,"normal":0.852385294317571}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8614573249999999,"event_time":"2026-01-08T12:00:10+00:00","arrival_time":"2026-01-08T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.13854267500000006,"normal":0.8614573249999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-08T12:00:10+00:00","arrival_time":"2026-01-08T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8614573249999999,"event_time":"2026-01-08T12:00:13+00:00","arrival_time":"2026-01-08T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.13854267500000006,"normal":0.8614573249999999},"reference_distribution":{"anomalous":0.13854267500000006,"normal":0.8614573249999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-08T12:00:13+00:00","arrival_time":"2026-01-08T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.852385294317571,"event_time":"2026-01-08T12:00:20+00:00","arrival_time":"2026-01-08T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.13854267500000006,"normal":0.8614573249999999},"reference_distribution":{"anomalous":0.147614705682429,"normal":0.852385294317571}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-007-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-08T12:00:20+00:00","arrival_time":"2026-01-08T12:00:31+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":7,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"6e51f109ecce8fa215949980cb3b5c749096309ca60a26dd7fbffb261fc8f65f"}}
{"id":"evaluation-v1-belief_preservation-20260725-008","name":"Evaluation v1.0 trajectory: belief_preservation case 008","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-008","label":"Distractor 008","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9286,"modality":"semantic_status","timestamp":"2026-01-09T12:00:10Z","metadata":{"arrival_time":"2026-01-09T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53112,"modality":"semantic_status","timestamp":"2026-01-09T12:00:20Z","metadata":{"arrival_time":"2026-01-09T12:00:32+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-008","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-01-09T12:00:14Z","metadata":{"arrival_time":"2026-01-09T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-09T12:00:10+00:00","obs-2":"2026-01-09T12:00:20+00:00","obs-distractor":"2026-01-09T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-09T12:00:10+00:00","obs-2":"2026-01-09T12:00:32+00:00","obs-distractor":"2026-01-09T12:00:14+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.974,"edge-ai-1":0.608},"confidence":{"obs-1":0.9286,"obs-2":0.53112,"obs-distractor":0.68},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-008-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.911537856507891,"event_time":"2026-01-09T12:00:20+00:00","arrival_time":"2026-01-09T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.08254360000000005,"normal":0.9174564},"reference_distribution":{"anomalous":0.08846214349210903,"normal":0.911537856507891}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9174564,"event_time":"2026-01-09T12:00:10+00:00","arrival_time":"2026-01-09T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.08254360000000005,"normal":0.9174564}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-09T12:00:10+00:00","arrival_time":"2026-01-09T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.9174564,"event_time":"2026-01-09T12:00:14+00:00","arrival_time":"2026-01-09T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.08254360000000005,"normal":0.9174564},"reference_distribution":{"anomalous":0.08254360000000005,"normal":0.9174564}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-09T12:00:14+00:00","arrival_time":"2026-01-09T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.911537856507891,"event_time":"2026-01-09T12:00:20+00:00","arrival_time":"2026-01-09T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.08254360000000005,"normal":0.9174564},"reference_distribution":{"anomalous":0.08846214349210903,"normal":0.911537856507891}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-008-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-09T12:00:20+00:00","arrival_time":"2026-01-09T12:00:32+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":8,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"99037ecfe9e1fd9dd1076b24f0e4067ce468d6050d6488cc591f614a97ec6a6b"}}
{"id":"evaluation-v1-belief_preservation-20260725-009","name":"Evaluation v1.0 trajectory: belief_preservation case 009","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-009","label":"Distractor 009","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.928425,"modality":"semantic_status","timestamp":"2026-01-10T12:00:10Z","metadata":{"arrival_time":"2026-01-10T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53126,"modality":"semantic_status","timestamp":"2026-01-10T12:00:20Z","metadata":{"arrival_time":"2026-01-10T12:00:33+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-009","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-01-10T12:00:12Z","metadata":{"arrival_time":"2026-01-10T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-10T12:00:10+00:00","obs-2":"2026-01-10T12:00:20+00:00","obs-distractor":"2026-01-10T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-10T12:00:10+00:00","obs-2":"2026-01-10T12:00:33+00:00","obs-distractor":"2026-01-10T12:00:12+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.91,"edge-ai-1":0.619},"confidence":{"obs-1":0.928425,"obs-2":0.53126,"obs-distractor":0.69},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-009-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.859796444513008,"event_time":"2026-01-10T12:00:20+00:00","arrival_time":"2026-01-10T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.13112607500000006,"normal":0.8688739249999999},"reference_distribution":{"anomalous":0.1402035554869921,"normal":0.859796444513008}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8688739249999999,"event_time":"2026-01-10T12:00:10+00:00","arrival_time":"2026-01-10T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.13112607500000006,"normal":0.8688739249999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-10T12:00:10+00:00","arrival_time":"2026-01-10T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8688739249999999,"event_time":"2026-01-10T12:00:12+00:00","arrival_time":"2026-01-10T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.13112607500000006,"normal":0.8688739249999999},"reference_distribution":{"anomalous":0.13112607500000006,"normal":0.8688739249999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-10T12:00:12+00:00","arrival_time":"2026-01-10T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.859796444513008,"event_time":"2026-01-10T12:00:20+00:00","arrival_time":"2026-01-10T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.13112607500000006,"normal":0.8688739249999999},"reference_distribution":{"anomalous":0.1402035554869921,"normal":0.859796444513008}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-009-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-10T12:00:20+00:00","arrival_time":"2026-01-10T12:00:33+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":9,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"662e80c9ff52214241ebe7c7a429ef2db49390593bedc19f840d067740e1bfee"}}
{"id":"evaluation-v1-belief_preservation-20260725-010","name":"Evaluation v1.0 trajectory: belief_preservation case 010","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-010","label":"Distractor 010","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.92825,"modality":"semantic_status","timestamp":"2026-01-11T12:00:10Z","metadata":{"arrival_time":"2026-01-11T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-010","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.7,"modality":"semantic_status","timestamp":"2026-01-11T12:00:13Z","metadata":{"arrival_time":"2026-01-11T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.5314,"modality":"semantic_status","timestamp":"2026-01-11T12:00:20Z","metadata":{"arrival_time":"2026-01-11T12:00:34+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-01-11T12:00:10+00:00","obs-distractor":"2026-01-11T12:00:13+00:00","obs-2":"2026-01-11T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-11T12:00:10+00:00","obs-distractor":"2026-01-11T12:00:13+00:00","obs-2":"2026-01-11T12:00:34+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.918,"edge-ai-1":0.63},"confidence":{"obs-1":0.92825,"obs-distractor":0.7,"obs-2":0.5314},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-010-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8853385609299597,"event_time":"2026-01-11T12:00:20+00:00","arrival_time":"2026-01-11T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10686649999999998,"normal":0.8931335},"reference_distribution":{"anomalous":0.1146614390700403,"normal":0.8853385609299597}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8931335,"event_time":"2026-01-11T12:00:10+00:00","arrival_time":"2026-01-11T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10686649999999998,"normal":0.8931335}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-11T12:00:10+00:00","arrival_time":"2026-01-11T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8931335,"event_time":"2026-01-11T12:00:13+00:00","arrival_time":"2026-01-11T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10686649999999998,"normal":0.8931335},"reference_distribution":{"anomalous":0.10686649999999998,"normal":0.8931335}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-11T12:00:13+00:00","arrival_time":"2026-01-11T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8853385609299597,"event_time":"2026-01-11T12:00:20+00:00","arrival_time":"2026-01-11T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10686649999999998,"normal":0.8931335},"reference_distribution":{"anomalous":0.1146614390700403,"normal":0.8853385609299597}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-010-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-11T12:00:20+00:00","arrival_time":"2026-01-11T12:00:34+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":10,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"8776e8a01b4886edbdfd237b3b9e909e76371c2a1e168efdccb1189a52baf07f"}}
{"id":"evaluation-v1-belief_preservation-20260725-011","name":"Evaluation v1.0 trajectory: belief_preservation case 011","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-011","label":"Distractor 011","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.928075,"modality":"semantic_status","timestamp":"2026-01-12T12:00:10Z","metadata":{"arrival_time":"2026-01-12T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-011","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.71,"modality":"semantic_status","timestamp":"2026-01-12T12:00:14Z","metadata":{"arrival_time":"2026-01-12T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53154,"modality":"semantic_status","timestamp":"2026-01-12T12:00:20Z","metadata":{"arrival_time":"2026-01-12T12:00:35+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-01-12T12:00:10+00:00","obs-distractor":"2026-01-12T12:00:14+00:00","obs-2":"2026-01-12T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-12T12:00:10+00:00","obs-distractor":"2026-01-12T12:00:14+00:00","obs-2":"2026-01-12T12:00:35+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.926,"edge-ai-1":0.641},"confidence":{"obs-1":0.928075,"obs-distractor":0.71,"obs-2":0.53154},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-011-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8223864024608167,"event_time":"2026-01-12T12:00:20+00:00","arrival_time":"2026-01-12T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1661015,"normal":0.8338985},"reference_distribution":{"anomalous":0.1776135975391833,"normal":0.8223864024608167}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8338985,"event_time":"2026-01-12T12:00:10+00:00","arrival_time":"2026-01-12T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1661015,"normal":0.8338985}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-12T12:00:10+00:00","arrival_time":"2026-01-12T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8338985,"event_time":"2026-01-12T12:00:14+00:00","arrival_time":"2026-01-12T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1661015,"normal":0.8338985},"reference_distribution":{"anomalous":0.1661015,"normal":0.8338985}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-12T12:00:14+00:00","arrival_time":"2026-01-12T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8223864024608167,"event_time":"2026-01-12T12:00:20+00:00","arrival_time":"2026-01-12T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1661015,"normal":0.8338985},"reference_distribution":{"anomalous":0.1776135975391833,"normal":0.8223864024608167}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-011-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-12T12:00:20+00:00","arrival_time":"2026-01-12T12:00:35+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":11,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"d5656c864c0ebb7bd9da11ed7c62b956fa98588f164929d10eea01cdf7e68c4c"}}
{"id":"evaluation-v1-belief_preservation-20260725-012","name":"Evaluation v1.0 trajectory: belief_preservation case 012","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-012","label":"Distractor 012","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9279,"modality":"semantic_status","timestamp":"2026-01-13T12:00:10Z","metadata":{"arrival_time":"2026-01-13T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-012","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.72,"modality":"semantic_status","timestamp":"2026-01-13T12:00:12Z","metadata":{"arrival_time":"2026-01-13T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53168,"modality":"semantic_status","timestamp":"2026-01-13T12:00:20Z","metadata":{"arrival_time":"2026-01-13T12:00:36+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-01-13T12:00:10+00:00","obs-distractor":"2026-01-13T12:00:12+00:00","obs-2":"2026-01-13T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-13T12:00:10+00:00","obs-distractor":"2026-01-13T12:00:12+00:00","obs-2":"2026-01-13T12:00:36+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.934,"edge-ai-1":0.652},"confidence":{"obs-1":0.9279,"obs-distractor":0.72,"obs-2":0.53168},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-012-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8919454224944562,"event_time":"2026-01-13T12:00:20+00:00","arrival_time":"2026-01-13T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10034140000000003,"normal":0.8996586},"reference_distribution":{"anomalous":0.10805457750554387,"normal":0.8919454224944562}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8996586,"event_time":"2026-01-13T12:00:10+00:00","arrival_time":"2026-01-13T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10034140000000003,"normal":0.8996586}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-13T12:00:10+00:00","arrival_time":"2026-01-13T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8996586,"event_time":"2026-01-13T12:00:12+00:00","arrival_time":"2026-01-13T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10034140000000003,"normal":0.8996586},"reference_distribution":{"anomalous":0.10034140000000003,"normal":0.8996586}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-13T12:00:12+00:00","arrival_time":"2026-01-13T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8919454224944562,"event_time":"2026-01-13T12:00:20+00:00","arrival_time":"2026-01-13T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10034140000000003,"normal":0.8996586},"reference_distribution":{"anomalous":0.10805457750554387,"normal":0.8919454224944562}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-012-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-13T12:00:20+00:00","arrival_time":"2026-01-13T12:00:36+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":12,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"eee1492e71c3f6cb1364f00439688a2182a2887b25ad096e9bc3a6d505e90d05"}}
{"id":"evaluation-v1-belief_preservation-20260725-013","name":"Evaluation v1.0 trajectory: belief_preservation case 013","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-013","label":"Distractor 013","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.927725,"modality":"semantic_status","timestamp":"2026-01-14T12:00:10Z","metadata":{"arrival_time":"2026-01-14T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-013","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.73,"modality":"semantic_status","timestamp":"2026-01-14T12:00:13Z","metadata":{"arrival_time":"2026-01-14T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53182,"modality":"semantic_status","timestamp":"2026-01-14T12:00:20Z","metadata":{"arrival_time":"2026-01-14T12:00:37+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-01-14T12:00:10+00:00","obs-distractor":"2026-01-14T12:00:13+00:00","obs-2":"2026-01-14T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-14T12:00:10+00:00","obs-distractor":"2026-01-14T12:00:13+00:00","obs-2":"2026-01-14T12:00:37+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.942,"edge-ai-1":0.52},"confidence":{"obs-1":0.927725,"obs-distractor":0.73,"obs-2":0.53182},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-013-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8322847176769042,"event_time":"2026-01-14T12:00:20+00:00","arrival_time":"2026-01-14T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15867544999999994,"normal":0.8413245500000001},"reference_distribution":{"anomalous":0.16771528232309582,"normal":0.8322847176769042}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8413245500000001,"event_time":"2026-01-14T12:00:10+00:00","arrival_time":"2026-01-14T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.15867544999999994,"normal":0.8413245500000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-14T12:00:10+00:00","arrival_time":"2026-01-14T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8413245500000001,"event_time":"2026-01-14T12:00:13+00:00","arrival_time":"2026-01-14T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15867544999999994,"normal":0.8413245500000001},"reference_distribution":{"anomalous":0.15867544999999994,"normal":0.8413245500000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-14T12:00:13+00:00","arrival_time":"2026-01-14T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8322847176769042,"event_time":"2026-01-14T12:00:20+00:00","arrival_time":"2026-01-14T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15867544999999994,"normal":0.8413245500000001},"reference_distribution":{"anomalous":0.16771528232309582,"normal":0.8322847176769042}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-013-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-14T12:00:20+00:00","arrival_time":"2026-01-14T12:00:37+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":13,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"e694278aa6a1cc553e86f15e177b5070379b804cc7eb193dd7cd41d6ac98757a"}}
{"id":"evaluation-v1-belief_preservation-20260725-014","name":"Evaluation v1.0 trajectory: belief_preservation case 014","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-014","label":"Distractor 014","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.92755,"modality":"semantic_status","timestamp":"2026-01-15T12:00:10Z","metadata":{"arrival_time":"2026-01-15T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53196,"modality":"semantic_status","timestamp":"2026-01-15T12:00:20Z","metadata":{"arrival_time":"2026-01-15T12:00:38+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-014","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.74,"modality":"semantic_status","timestamp":"2026-01-15T12:00:14Z","metadata":{"arrival_time":"2026-01-15T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-15T12:00:10+00:00","obs-2":"2026-01-15T12:00:20+00:00","obs-distractor":"2026-01-15T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-15T12:00:10+00:00","obs-2":"2026-01-15T12:00:38+00:00","obs-distractor":"2026-01-15T12:00:14+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.95,"edge-ai-1":0.531},"confidence":{"obs-1":0.92755,"obs-2":0.53196,"obs-distractor":0.74},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-014-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.9002371688998065,"event_time":"2026-01-15T12:00:20+00:00","arrival_time":"2026-01-15T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09382749999999995,"normal":0.9061725},"reference_distribution":{"anomalous":0.09976283110019335,"normal":0.9002371688998065}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9061725,"event_time":"2026-01-15T12:00:10+00:00","arrival_time":"2026-01-15T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.09382749999999995,"normal":0.9061725}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-15T12:00:10+00:00","arrival_time":"2026-01-15T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.9061725,"event_time":"2026-01-15T12:00:14+00:00","arrival_time":"2026-01-15T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09382749999999995,"normal":0.9061725},"reference_distribution":{"anomalous":0.09382749999999995,"normal":0.9061725}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-15T12:00:14+00:00","arrival_time":"2026-01-15T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.9002371688998065,"event_time":"2026-01-15T12:00:20+00:00","arrival_time":"2026-01-15T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09382749999999995,"normal":0.9061725},"reference_distribution":{"anomalous":0.09976283110019335,"normal":0.9002371688998065}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-014-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-15T12:00:20+00:00","arrival_time":"2026-01-15T12:00:38+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":14,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"5c6bf68e2472d66f42079d4d31273e19be95846c2218407e398076e792449858"}}
{"id":"evaluation-v1-belief_preservation-20260725-015","name":"Evaluation v1.0 trajectory: belief_preservation case 015","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-015","label":"Distractor 015","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.927375,"modality":"semantic_status","timestamp":"2026-01-16T12:00:10Z","metadata":{"arrival_time":"2026-01-16T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-015","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.75,"modality":"semantic_status","timestamp":"2026-01-16T12:00:12Z","metadata":{"arrival_time":"2026-01-16T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.5321,"modality":"semantic_status","timestamp":"2026-01-16T12:00:20Z","metadata":{"arrival_time":"2026-01-16T12:00:39+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-01-16T12:00:10+00:00","obs-distractor":"2026-01-16T12:00:12+00:00","obs-2":"2026-01-16T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-16T12:00:10+00:00","obs-distractor":"2026-01-16T12:00:12+00:00","obs-2":"2026-01-16T12:00:39+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.958,"edge-ai-1":0.542},"confidence":{"obs-1":0.927375,"obs-distractor":0.75,"obs-2":0.5321},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-015-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8395813211301143,"event_time":"2026-01-16T12:00:20+00:00","arrival_time":"2026-01-16T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.151262,"normal":0.848738},"reference_distribution":{"anomalous":0.16041867886988567,"normal":0.8395813211301143}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.848738,"event_time":"2026-01-16T12:00:10+00:00","arrival_time":"2026-01-16T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.151262,"normal":0.848738}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-16T12:00:10+00:00","arrival_time":"2026-01-16T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.848738,"event_time":"2026-01-16T12:00:12+00:00","arrival_time":"2026-01-16T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.151262,"normal":0.848738},"reference_distribution":{"anomalous":0.151262,"normal":0.848738}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-16T12:00:12+00:00","arrival_time":"2026-01-16T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8395813211301143,"event_time":"2026-01-16T12:00:20+00:00","arrival_time":"2026-01-16T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.151262,"normal":0.848738},"reference_distribution":{"anomalous":0.16041867886988567,"normal":0.8395813211301143}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-015-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-16T12:00:20+00:00","arrival_time":"2026-01-16T12:00:39+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":15,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"bdc990cc7b1fa4f132c978a8681e9772331265ae074d36bbad7d9527b2259fc7"}}
{"id":"evaluation-v1-belief_preservation-20260725-016","name":"Evaluation v1.0 trajectory: belief_preservation case 016","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-016","label":"Distractor 016","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9272,"modality":"semantic_status","timestamp":"2026-01-17T12:00:10Z","metadata":{"arrival_time":"2026-01-17T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53224,"modality":"semantic_status","timestamp":"2026-01-17T12:00:20Z","metadata":{"arrival_time":"2026-01-17T12:00:40+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-016","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.76,"modality":"semantic_status","timestamp":"2026-01-17T12:00:13Z","metadata":{"arrival_time":"2026-01-17T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-17T12:00:10+00:00","obs-2":"2026-01-17T12:00:20+00:00","obs-distractor":"2026-01-17T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-17T12:00:10+00:00","obs-2":"2026-01-17T12:00:40+00:00","obs-distractor":"2026-01-17T12:00:13+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.966,"edge-ai-1":0.553},"confidence":{"obs-1":0.9272,"obs-2":0.53224,"obs-distractor":0.76},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-016-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.906819118811252,"event_time":"2026-01-17T12:00:20+00:00","arrival_time":"2026-01-17T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.08732479999999998,"normal":0.9126752},"reference_distribution":{"anomalous":0.09318088118874801,"normal":0.906819118811252}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9126752,"event_time":"2026-01-17T12:00:10+00:00","arrival_time":"2026-01-17T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.08732479999999998,"normal":0.9126752}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-17T12:00:10+00:00","arrival_time":"2026-01-17T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.9126752,"event_time":"2026-01-17T12:00:13+00:00","arrival_time":"2026-01-17T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.08732479999999998,"normal":0.9126752},"reference_distribution":{"anomalous":0.08732479999999998,"normal":0.9126752}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-17T12:00:13+00:00","arrival_time":"2026-01-17T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.906819118811252,"event_time":"2026-01-17T12:00:20+00:00","arrival_time":"2026-01-17T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.08732479999999998,"normal":0.9126752},"reference_distribution":{"anomalous":0.09318088118874801,"normal":0.906819118811252}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-016-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-17T12:00:20+00:00","arrival_time":"2026-01-17T12:00:40+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":16,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"1d921a2cc1b660c19064a582d61454f8f0cfdee23f84d9d8c339ebff2c720a3b"}}
{"id":"evaluation-v1-belief_preservation-20260725-017","name":"Evaluation v1.0 trajectory: belief_preservation case 017","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-017","label":"Distractor 017","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.927025,"modality":"semantic_status","timestamp":"2026-01-18T12:00:10Z","metadata":{"arrival_time":"2026-01-18T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53238,"modality":"semantic_status","timestamp":"2026-01-18T12:00:20Z","metadata":{"arrival_time":"2026-01-18T12:00:24+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-017","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.77,"modality":"semantic_status","timestamp":"2026-01-18T12:00:14Z","metadata":{"arrival_time":"2026-01-18T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-18T12:00:10+00:00","obs-2":"2026-01-18T12:00:20+00:00","obs-distractor":"2026-01-18T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-18T12:00:10+00:00","obs-2":"2026-01-18T12:00:24+00:00","obs-distractor":"2026-01-18T12:00:14+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.974,"edge-ai-1":0.564},"confidence":{"obs-1":0.927025,"obs-2":0.53238,"obs-distractor":0.77},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-017-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8469014083101658,"event_time":"2026-01-18T12:00:20+00:00","arrival_time":"2026-01-18T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.14386115,"normal":0.85613885},"reference_distribution":{"anomalous":0.15309859168983414,"normal":0.8469014083101658}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.85613885,"event_time":"2026-01-18T12:00:10+00:00","arrival_time":"2026-01-18T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.14386115,"normal":0.85613885}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-18T12:00:10+00:00","arrival_time":"2026-01-18T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.85613885,"event_time":"2026-01-18T12:00:14+00:00","arrival_time":"2026-01-18T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.14386115,"normal":0.85613885},"reference_distribution":{"anomalous":0.14386115,"normal":0.85613885}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-18T12:00:14+00:00","arrival_time":"2026-01-18T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8469014083101658,"event_time":"2026-01-18T12:00:20+00:00","arrival_time":"2026-01-18T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.14386115,"normal":0.85613885},"reference_distribution":{"anomalous":0.15309859168983414,"normal":0.8469014083101658}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-017-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-18T12:00:20+00:00","arrival_time":"2026-01-18T12:00:24+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":17,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"fd18adba2d84b92737a23bf5e14ee23b14dad759c329f8c3ea4f4a58ddc7b789"}}
{"id":"evaluation-v1-belief_preservation-20260725-018","name":"Evaluation v1.0 trajectory: belief_preservation case 018","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-018","label":"Distractor 018","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.92685,"modality":"semantic_status","timestamp":"2026-01-19T12:00:10Z","metadata":{"arrival_time":"2026-01-19T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-018","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.78,"modality":"semantic_status","timestamp":"2026-01-19T12:00:12Z","metadata":{"arrival_time":"2026-01-19T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53252,"modality":"semantic_status","timestamp":"2026-01-19T12:00:20Z","metadata":{"arrival_time":"2026-01-19T12:00:25+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-01-19T12:00:10+00:00","obs-distractor":"2026-01-19T12:00:12+00:00","obs-2":"2026-01-19T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-19T12:00:10+00:00","obs-distractor":"2026-01-19T12:00:12+00:00","obs-2":"2026-01-19T12:00:25+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.91,"edge-ai-1":0.575},"confidence":{"obs-1":0.92685,"obs-distractor":0.78,"obs-2":0.53252},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-018-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8807979257386536,"event_time":"2026-01-19T12:00:20+00:00","arrival_time":"2026-01-19T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.11156650000000001,"normal":0.8884335},"reference_distribution":{"anomalous":0.11920207426134645,"normal":0.8807979257386536}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8884335,"event_time":"2026-01-19T12:00:10+00:00","arrival_time":"2026-01-19T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11156650000000001,"normal":0.8884335}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-19T12:00:10+00:00","arrival_time":"2026-01-19T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8884335,"event_time":"2026-01-19T12:00:12+00:00","arrival_time":"2026-01-19T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.11156650000000001,"normal":0.8884335},"reference_distribution":{"anomalous":0.11156650000000001,"normal":0.8884335}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-19T12:00:12+00:00","arrival_time":"2026-01-19T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8807979257386536,"event_time":"2026-01-19T12:00:20+00:00","arrival_time":"2026-01-19T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.11156650000000001,"normal":0.8884335},"reference_distribution":{"anomalous":0.11920207426134645,"normal":0.8807979257386536}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-018-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-19T12:00:20+00:00","arrival_time":"2026-01-19T12:00:25+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":18,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"59725285af4c80dcaf56f90a06806db18bcb0cd4e521840151faf039b997085d"}}
{"id":"evaluation-v1-belief_preservation-20260725-019","name":"Evaluation v1.0 trajectory: belief_preservation case 019","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-019","label":"Distractor 019","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.926675,"modality":"semantic_status","timestamp":"2026-01-20T12:00:10Z","metadata":{"arrival_time":"2026-01-20T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53266,"modality":"semantic_status","timestamp":"2026-01-20T12:00:20Z","metadata":{"arrival_time":"2026-01-20T12:00:26+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-019","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.79,"modality":"semantic_status","timestamp":"2026-01-20T12:00:13Z","metadata":{"arrival_time":"2026-01-20T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-20T12:00:10+00:00","obs-2":"2026-01-20T12:00:20+00:00","obs-distractor":"2026-01-20T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-20T12:00:10+00:00","obs-2":"2026-01-20T12:00:26+00:00","obs-distractor":"2026-01-20T12:00:13+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.918,"edge-ai-1":0.586},"confidence":{"obs-1":0.926675,"obs-2":0.53266,"obs-distractor":0.79},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-019-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8542469736504013,"event_time":"2026-01-20T12:00:20+00:00","arrival_time":"2026-01-20T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1364729,"normal":0.8635271},"reference_distribution":{"anomalous":0.14575302634959886,"normal":0.8542469736504013}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8635271,"event_time":"2026-01-20T12:00:10+00:00","arrival_time":"2026-01-20T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1364729,"normal":0.8635271}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-20T12:00:10+00:00","arrival_time":"2026-01-20T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8635271,"event_time":"2026-01-20T12:00:13+00:00","arrival_time":"2026-01-20T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1364729,"normal":0.8635271},"reference_distribution":{"anomalous":0.1364729,"normal":0.8635271}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-20T12:00:13+00:00","arrival_time":"2026-01-20T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8542469736504013,"event_time":"2026-01-20T12:00:20+00:00","arrival_time":"2026-01-20T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1364729,"normal":0.8635271},"reference_distribution":{"anomalous":0.14575302634959886,"normal":0.8542469736504013}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-019-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-20T12:00:20+00:00","arrival_time":"2026-01-20T12:00:26+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":19,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"f28c8856b27cb6258fbd49aa87ee71f8271b96a822ab14c8871d39d6eff1ab5c"}}
{"id":"evaluation-v1-belief_preservation-20260725-020","name":"Evaluation v1.0 trajectory: belief_preservation case 020","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-020","label":"Distractor 020","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9265,"modality":"semantic_status","timestamp":"2026-01-21T12:00:10Z","metadata":{"arrival_time":"2026-01-21T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-020","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-01-21T12:00:14Z","metadata":{"arrival_time":"2026-01-21T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.5328,"modality":"semantic_status","timestamp":"2026-01-21T12:00:20Z","metadata":{"arrival_time":"2026-01-21T12:00:27+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-01-21T12:00:10+00:00","obs-distractor":"2026-01-21T12:00:14+00:00","obs-2":"2026-01-21T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-21T12:00:10+00:00","obs-distractor":"2026-01-21T12:00:14+00:00","obs-2":"2026-01-21T12:00:27+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.926,"edge-ai-1":0.597},"confidence":{"obs-1":0.9265,"obs-distractor":0.6,"obs-2":0.5328},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-020-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.887339415618356,"event_time":"2026-01-21T12:00:20+00:00","arrival_time":"2026-01-21T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10506100000000007,"normal":0.8949389999999999},"reference_distribution":{"anomalous":0.11266058438164388,"normal":0.887339415618356}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8949389999999999,"event_time":"2026-01-21T12:00:10+00:00","arrival_time":"2026-01-21T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10506100000000007,"normal":0.8949389999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-21T12:00:10+00:00","arrival_time":"2026-01-21T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8949389999999999,"event_time":"2026-01-21T12:00:14+00:00","arrival_time":"2026-01-21T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10506100000000007,"normal":0.8949389999999999},"reference_distribution":{"anomalous":0.10506100000000007,"normal":0.8949389999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-21T12:00:14+00:00","arrival_time":"2026-01-21T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.887339415618356,"event_time":"2026-01-21T12:00:20+00:00","arrival_time":"2026-01-21T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10506100000000007,"normal":0.8949389999999999},"reference_distribution":{"anomalous":0.11266058438164388,"normal":0.887339415618356}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-020-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-21T12:00:20+00:00","arrival_time":"2026-01-21T12:00:27+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":20,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"199c013f25e64529860b0e49c13d3bb6eb5756ad2ca249eea60c9b9349d97ea7"}}
{"id":"evaluation-v1-belief_preservation-20260725-021","name":"Evaluation v1.0 trajectory: belief_preservation case 021","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-021","label":"Distractor 021","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.926325,"modality":"semantic_status","timestamp":"2026-01-22T12:00:10Z","metadata":{"arrival_time":"2026-01-22T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-021","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-01-22T12:00:12Z","metadata":{"arrival_time":"2026-01-22T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53294,"modality":"semantic_status","timestamp":"2026-01-22T12:00:20Z","metadata":{"arrival_time":"2026-01-22T12:00:28+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-01-22T12:00:10+00:00","obs-distractor":"2026-01-22T12:00:12+00:00","obs-2":"2026-01-22T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-22T12:00:10+00:00","obs-distractor":"2026-01-22T12:00:12+00:00","obs-2":"2026-01-22T12:00:28+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.934,"edge-ai-1":0.608},"confidence":{"obs-1":0.926325,"obs-distractor":0.61,"obs-2":0.53294},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-021-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8616200646924481,"event_time":"2026-01-22T12:00:20+00:00","arrival_time":"2026-01-22T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.12909725000000005,"normal":0.87090275},"reference_distribution":{"anomalous":0.1383799353075519,"normal":0.8616200646924481}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.87090275,"event_time":"2026-01-22T12:00:10+00:00","arrival_time":"2026-01-22T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.12909725000000005,"normal":0.87090275}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-22T12:00:10+00:00","arrival_time":"2026-01-22T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.87090275,"event_time":"2026-01-22T12:00:12+00:00","arrival_time":"2026-01-22T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.12909725000000005,"normal":0.87090275},"reference_distribution":{"anomalous":0.12909725000000005,"normal":0.87090275}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-22T12:00:12+00:00","arrival_time":"2026-01-22T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8616200646924481,"event_time":"2026-01-22T12:00:20+00:00","arrival_time":"2026-01-22T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.12909725000000005,"normal":0.87090275},"reference_distribution":{"anomalous":0.1383799353075519,"normal":0.8616200646924481}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-021-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-22T12:00:20+00:00","arrival_time":"2026-01-22T12:00:28+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":21,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c805f18379b078599c7c8d6d7aa701dee8e8a82882c2b771be3513e8cdce089e"}}
{"id":"evaluation-v1-belief_preservation-20260725-022","name":"Evaluation v1.0 trajectory: belief_preservation case 022","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-022","label":"Distractor 022","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.92615,"modality":"semantic_status","timestamp":"2026-01-23T12:00:10Z","metadata":{"arrival_time":"2026-01-23T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53308,"modality":"semantic_status","timestamp":"2026-01-23T12:00:20Z","metadata":{"arrival_time":"2026-01-23T12:00:29+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-022","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-01-23T12:00:13Z","metadata":{"arrival_time":"2026-01-23T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-23T12:00:10+00:00","obs-2":"2026-01-23T12:00:20+00:00","obs-distractor":"2026-01-23T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-23T12:00:10+00:00","obs-2":"2026-01-23T12:00:29+00:00","obs-distractor":"2026-01-23T12:00:13+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.942,"edge-ai-1":0.619},"confidence":{"obs-1":0.92615,"obs-2":0.53308,"obs-distractor":0.62},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-022-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8939084211283314,"event_time":"2026-01-23T12:00:20+00:00","arrival_time":"2026-01-23T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09856670000000001,"normal":0.9014333},"reference_distribution":{"anomalous":0.10609157887166867,"normal":0.8939084211283314}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9014333,"event_time":"2026-01-23T12:00:10+00:00","arrival_time":"2026-01-23T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.09856670000000001,"normal":0.9014333}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-23T12:00:10+00:00","arrival_time":"2026-01-23T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.9014333,"event_time":"2026-01-23T12:00:13+00:00","arrival_time":"2026-01-23T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09856670000000001,"normal":0.9014333},"reference_distribution":{"anomalous":0.09856670000000001,"normal":0.9014333}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-23T12:00:13+00:00","arrival_time":"2026-01-23T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8939084211283314,"event_time":"2026-01-23T12:00:20+00:00","arrival_time":"2026-01-23T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09856670000000001,"normal":0.9014333},"reference_distribution":{"anomalous":0.10609157887166867,"normal":0.8939084211283314}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-022-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-23T12:00:20+00:00","arrival_time":"2026-01-23T12:00:29+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":22,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"395903b3620edc4052b839b3c45bbf47963eb7578dea04ee1bdd38af5d6c14b7"}}
{"id":"evaluation-v1-belief_preservation-20260725-023","name":"Evaluation v1.0 trajectory: belief_preservation case 023","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-023","label":"Distractor 023","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.925975,"modality":"semantic_status","timestamp":"2026-01-24T12:00:10Z","metadata":{"arrival_time":"2026-01-24T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-023","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-01-24T12:00:14Z","metadata":{"arrival_time":"2026-01-24T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53322,"modality":"semantic_status","timestamp":"2026-01-24T12:00:20Z","metadata":{"arrival_time":"2026-01-24T12:00:30+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-01-24T12:00:10+00:00","obs-distractor":"2026-01-24T12:00:14+00:00","obs-2":"2026-01-24T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-24T12:00:10+00:00","obs-distractor":"2026-01-24T12:00:14+00:00","obs-2":"2026-01-24T12:00:30+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.95,"edge-ai-1":0.63},"confidence":{"obs-1":0.925975,"obs-distractor":0.63,"obs-2":0.53322},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-023-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8242898723341898,"event_time":"2026-01-24T12:00:20+00:00","arrival_time":"2026-01-24T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.163905725,"normal":0.836094275},"reference_distribution":{"anomalous":0.17571012766581012,"normal":0.8242898723341898}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.836094275,"event_time":"2026-01-24T12:00:10+00:00","arrival_time":"2026-01-24T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.163905725,"normal":0.836094275}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-24T12:00:10+00:00","arrival_time":"2026-01-24T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.836094275,"event_time":"2026-01-24T12:00:14+00:00","arrival_time":"2026-01-24T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.163905725,"normal":0.836094275},"reference_distribution":{"anomalous":0.163905725,"normal":0.836094275}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-24T12:00:14+00:00","arrival_time":"2026-01-24T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8242898723341898,"event_time":"2026-01-24T12:00:20+00:00","arrival_time":"2026-01-24T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.163905725,"normal":0.836094275},"reference_distribution":{"anomalous":0.17571012766581012,"normal":0.8242898723341898}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-023-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-24T12:00:20+00:00","arrival_time":"2026-01-24T12:00:30+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":23,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"4c21e98f88ef642db60452f4934a33be099bf4737c76784d28fac6fc339162ec"}}
{"id":"evaluation-v1-belief_preservation-20260725-024","name":"Evaluation v1.0 trajectory: belief_preservation case 024","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-024","label":"Distractor 024","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9258,"modality":"semantic_status","timestamp":"2026-01-25T12:00:10Z","metadata":{"arrival_time":"2026-01-25T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53336,"modality":"semantic_status","timestamp":"2026-01-25T12:00:20Z","metadata":{"arrival_time":"2026-01-25T12:00:31+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-024","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-01-25T12:00:12Z","metadata":{"arrival_time":"2026-01-25T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-25T12:00:10+00:00","obs-2":"2026-01-25T12:00:20+00:00","obs-distractor":"2026-01-25T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-25T12:00:10+00:00","obs-2":"2026-01-25T12:00:31+00:00","obs-distractor":"2026-01-25T12:00:12+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.958,"edge-ai-1":0.641},"confidence":{"obs-1":0.9258,"obs-2":0.53336,"obs-distractor":0.64},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-024-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.9005067803844383,"event_time":"2026-01-25T12:00:20+00:00","arrival_time":"2026-01-25T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09208360000000004,"normal":0.9079164},"reference_distribution":{"anomalous":0.09949321961556172,"normal":0.9005067803844383}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9079164,"event_time":"2026-01-25T12:00:10+00:00","arrival_time":"2026-01-25T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.09208360000000004,"normal":0.9079164}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-25T12:00:10+00:00","arrival_time":"2026-01-25T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.9079164,"event_time":"2026-01-25T12:00:12+00:00","arrival_time":"2026-01-25T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09208360000000004,"normal":0.9079164},"reference_distribution":{"anomalous":0.09208360000000004,"normal":0.9079164}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-25T12:00:12+00:00","arrival_time":"2026-01-25T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.9005067803844383,"event_time":"2026-01-25T12:00:20+00:00","arrival_time":"2026-01-25T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09208360000000004,"normal":0.9079164},"reference_distribution":{"anomalous":0.09949321961556172,"normal":0.9005067803844383}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-024-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-25T12:00:20+00:00","arrival_time":"2026-01-25T12:00:31+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":24,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"b03fb58e49ef9046aa813b3918345edb4511954b0a978d3f1b5d7a4a15c8b01d"}}
{"id":"evaluation-v1-belief_preservation-20260725-025","name":"Evaluation v1.0 trajectory: belief_preservation case 025","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-025","label":"Distractor 025","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.925625,"modality":"semantic_status","timestamp":"2026-01-26T12:00:10Z","metadata":{"arrival_time":"2026-01-26T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.5335,"modality":"semantic_status","timestamp":"2026-01-26T12:00:20Z","metadata":{"arrival_time":"2026-01-26T12:00:32+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-025","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-01-26T12:00:13Z","metadata":{"arrival_time":"2026-01-26T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-26T12:00:10+00:00","obs-2":"2026-01-26T12:00:20+00:00","obs-distractor":"2026-01-26T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-26T12:00:10+00:00","obs-2":"2026-01-26T12:00:32+00:00","obs-distractor":"2026-01-26T12:00:13+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.966,"edge-ai-1":0.652},"confidence":{"obs-1":0.925625,"obs-2":0.5335,"obs-distractor":0.65},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-025-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8315880355177907,"event_time":"2026-01-26T12:00:20+00:00","arrival_time":"2026-01-26T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15652062499999997,"normal":0.843479375},"reference_distribution":{"anomalous":0.16841196448220924,"normal":0.8315880355177907}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.843479375,"event_time":"2026-01-26T12:00:10+00:00","arrival_time":"2026-01-26T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.15652062499999997,"normal":0.843479375}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-26T12:00:10+00:00","arrival_time":"2026-01-26T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.843479375,"event_time":"2026-01-26T12:00:13+00:00","arrival_time":"2026-01-26T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15652062499999997,"normal":0.843479375},"reference_distribution":{"anomalous":0.15652062499999997,"normal":0.843479375}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-26T12:00:13+00:00","arrival_time":"2026-01-26T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8315880355177907,"event_time":"2026-01-26T12:00:20+00:00","arrival_time":"2026-01-26T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15652062499999997,"normal":0.843479375},"reference_distribution":{"anomalous":0.16841196448220924,"normal":0.8315880355177907}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-025-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-26T12:00:20+00:00","arrival_time":"2026-01-26T12:00:32+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":25,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"906214fa1d9971fd3de853ea06b04767ef05aa796ef01c1c308519680c7f7525"}}
{"id":"evaluation-v1-belief_preservation-20260725-026","name":"Evaluation v1.0 trajectory: belief_preservation case 026","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-026","label":"Distractor 026","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.92545,"modality":"semantic_status","timestamp":"2026-01-27T12:00:10Z","metadata":{"arrival_time":"2026-01-27T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53364,"modality":"semantic_status","timestamp":"2026-01-27T12:00:20Z","metadata":{"arrival_time":"2026-01-27T12:00:33+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-026","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-01-27T12:00:14Z","metadata":{"arrival_time":"2026-01-27T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-27T12:00:10+00:00","obs-2":"2026-01-27T12:00:20+00:00","obs-distractor":"2026-01-27T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-27T12:00:10+00:00","obs-2":"2026-01-27T12:00:33+00:00","obs-distractor":"2026-01-27T12:00:14+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.974,"edge-ai-1":0.52},"confidence":{"obs-1":0.92545,"obs-2":0.53364,"obs-distractor":0.66},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-026-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.9087472266404378,"event_time":"2026-01-27T12:00:20+00:00","arrival_time":"2026-01-27T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.08561170000000007,"normal":0.9143882999999999},"reference_distribution":{"anomalous":0.09125277335956211,"normal":0.9087472266404378}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9143882999999999,"event_time":"2026-01-27T12:00:10+00:00","arrival_time":"2026-01-27T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.08561170000000007,"normal":0.9143882999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-27T12:00:10+00:00","arrival_time":"2026-01-27T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.9143882999999999,"event_time":"2026-01-27T12:00:14+00:00","arrival_time":"2026-01-27T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.08561170000000007,"normal":0.9143882999999999},"reference_distribution":{"anomalous":0.08561170000000007,"normal":0.9143882999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-27T12:00:14+00:00","arrival_time":"2026-01-27T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.9087472266404378,"event_time":"2026-01-27T12:00:20+00:00","arrival_time":"2026-01-27T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.08561170000000007,"normal":0.9143882999999999},"reference_distribution":{"anomalous":0.09125277335956211,"normal":0.9087472266404378}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-026-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-27T12:00:20+00:00","arrival_time":"2026-01-27T12:00:33+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":26,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"740ee34fde359244521f6835de22995d0123ed6983b7d4c35e071323bb594789"}}
{"id":"evaluation-v1-belief_preservation-20260725-027","name":"Evaluation v1.0 trajectory: belief_preservation case 027","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-027","label":"Distractor 027","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.925275,"modality":"semantic_status","timestamp":"2026-01-28T12:00:10Z","metadata":{"arrival_time":"2026-01-28T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53378,"modality":"semantic_status","timestamp":"2026-01-28T12:00:20Z","metadata":{"arrival_time":"2026-01-28T12:00:34+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-027","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-01-28T12:00:12Z","metadata":{"arrival_time":"2026-01-28T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-28T12:00:10+00:00","obs-2":"2026-01-28T12:00:20+00:00","obs-distractor":"2026-01-28T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-28T12:00:10+00:00","obs-2":"2026-01-28T12:00:34+00:00","obs-distractor":"2026-01-28T12:00:12+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.91,"edge-ai-1":0.531},"confidence":{"obs-1":0.925275,"obs-2":0.53378,"obs-distractor":0.67},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-027-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8415116262283573,"event_time":"2026-01-28T12:00:20+00:00","arrival_time":"2026-01-28T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.14914812500000008,"normal":0.8508518749999999},"reference_distribution":{"anomalous":0.1584883737716427,"normal":0.8415116262283573}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8508518749999999,"event_time":"2026-01-28T12:00:10+00:00","arrival_time":"2026-01-28T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.14914812500000008,"normal":0.8508518749999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-28T12:00:10+00:00","arrival_time":"2026-01-28T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8508518749999999,"event_time":"2026-01-28T12:00:12+00:00","arrival_time":"2026-01-28T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.14914812500000008,"normal":0.8508518749999999},"reference_distribution":{"anomalous":0.14914812500000008,"normal":0.8508518749999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-28T12:00:12+00:00","arrival_time":"2026-01-28T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8415116262283573,"event_time":"2026-01-28T12:00:20+00:00","arrival_time":"2026-01-28T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.14914812500000008,"normal":0.8508518749999999},"reference_distribution":{"anomalous":0.1584883737716427,"normal":0.8415116262283573}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-027-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-28T12:00:20+00:00","arrival_time":"2026-01-28T12:00:34+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":27,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"01ab727fc9abf0d69cae9c041036b0772b20e3b18028f82e750492603454597e"}}
{"id":"evaluation-v1-belief_preservation-20260725-028","name":"Evaluation v1.0 trajectory: belief_preservation case 028","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-028","label":"Distractor 028","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9251,"modality":"semantic_status","timestamp":"2026-01-29T12:00:10Z","metadata":{"arrival_time":"2026-01-29T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-028","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-01-29T12:00:13Z","metadata":{"arrival_time":"2026-01-29T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53392,"modality":"semantic_status","timestamp":"2026-01-29T12:00:20Z","metadata":{"arrival_time":"2026-01-29T12:00:35+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-01-29T12:00:10+00:00","obs-distractor":"2026-01-29T12:00:13+00:00","obs-2":"2026-01-29T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-29T12:00:10+00:00","obs-distractor":"2026-01-29T12:00:13+00:00","obs-2":"2026-01-29T12:00:35+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.918,"edge-ai-1":0.542},"confidence":{"obs-1":0.9251,"obs-distractor":0.68,"obs-2":0.53392},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-028-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8828439466789983,"event_time":"2026-01-29T12:00:20+00:00","arrival_time":"2026-01-29T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10975819999999992,"normal":0.8902418000000001},"reference_distribution":{"anomalous":0.11715605332100165,"normal":0.8828439466789983}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8902418000000001,"event_time":"2026-01-29T12:00:10+00:00","arrival_time":"2026-01-29T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10975819999999992,"normal":0.8902418000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-29T12:00:10+00:00","arrival_time":"2026-01-29T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8902418000000001,"event_time":"2026-01-29T12:00:13+00:00","arrival_time":"2026-01-29T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10975819999999992,"normal":0.8902418000000001},"reference_distribution":{"anomalous":0.10975819999999992,"normal":0.8902418000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-29T12:00:13+00:00","arrival_time":"2026-01-29T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8828439466789983,"event_time":"2026-01-29T12:00:20+00:00","arrival_time":"2026-01-29T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10975819999999992,"normal":0.8902418000000001},"reference_distribution":{"anomalous":0.11715605332100165,"normal":0.8828439466789983}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-028-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-29T12:00:20+00:00","arrival_time":"2026-01-29T12:00:35+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":28,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"12628b2f66b5c9ea1bd2b31476bf2b67931ce3feb7106895406acd9bfcd74966"}}
{"id":"evaluation-v1-belief_preservation-20260725-029","name":"Evaluation v1.0 trajectory: belief_preservation case 029","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-029","label":"Distractor 029","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.924925,"modality":"semantic_status","timestamp":"2026-01-30T12:00:10Z","metadata":{"arrival_time":"2026-01-30T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-029","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-01-30T12:00:14Z","metadata":{"arrival_time":"2026-01-30T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53406,"modality":"semantic_status","timestamp":"2026-01-30T12:00:20Z","metadata":{"arrival_time":"2026-01-30T12:00:36+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-01-30T12:00:10+00:00","obs-distractor":"2026-01-30T12:00:14+00:00","obs-2":"2026-01-30T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-30T12:00:10+00:00","obs-distractor":"2026-01-30T12:00:14+00:00","obs-2":"2026-01-30T12:00:36+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.926,"edge-ai-1":0.553},"confidence":{"obs-1":0.924925,"obs-distractor":0.69,"obs-2":0.53406},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-029-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.848789708292788,"event_time":"2026-01-30T12:00:20+00:00","arrival_time":"2026-01-30T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.141788225,"normal":0.858211775},"reference_distribution":{"anomalous":0.15121029170721195,"normal":0.848789708292788}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.858211775,"event_time":"2026-01-30T12:00:10+00:00","arrival_time":"2026-01-30T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.141788225,"normal":0.858211775}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-30T12:00:10+00:00","arrival_time":"2026-01-30T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.858211775,"event_time":"2026-01-30T12:00:14+00:00","arrival_time":"2026-01-30T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.141788225,"normal":0.858211775},"reference_distribution":{"anomalous":0.141788225,"normal":0.858211775}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-30T12:00:14+00:00","arrival_time":"2026-01-30T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.848789708292788,"event_time":"2026-01-30T12:00:20+00:00","arrival_time":"2026-01-30T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.141788225,"normal":0.858211775},"reference_distribution":{"anomalous":0.15121029170721195,"normal":0.848789708292788}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-029-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-30T12:00:20+00:00","arrival_time":"2026-01-30T12:00:36+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":29,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c965041cbcff60d31fd09c08409fb3511365ad1db1ae45174d2728d1e9edf02c"}}
{"id":"evaluation-v1-belief_preservation-20260725-030","name":"Evaluation v1.0 trajectory: belief_preservation case 030","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-030","label":"Distractor 030","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.92475,"modality":"semantic_status","timestamp":"2026-01-31T12:00:10Z","metadata":{"arrival_time":"2026-01-31T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.5342,"modality":"semantic_status","timestamp":"2026-01-31T12:00:20Z","metadata":{"arrival_time":"2026-01-31T12:00:37+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-030","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.7,"modality":"semantic_status","timestamp":"2026-01-31T12:00:12Z","metadata":{"arrival_time":"2026-01-31T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-31T12:00:10+00:00","obs-2":"2026-01-31T12:00:20+00:00","obs-distractor":"2026-01-31T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-31T12:00:10+00:00","obs-2":"2026-01-31T12:00:37+00:00","obs-distractor":"2026-01-31T12:00:12+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.934,"edge-ai-1":0.564},"confidence":{"obs-1":0.92475,"obs-2":0.5342,"obs-distractor":0.7},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-030-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8893450621276717,"event_time":"2026-01-31T12:00:20+00:00","arrival_time":"2026-01-31T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10328350000000008,"normal":0.8967164999999999},"reference_distribution":{"anomalous":0.1106549378723283,"normal":0.8893450621276717}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8967164999999999,"event_time":"2026-01-31T12:00:10+00:00","arrival_time":"2026-01-31T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10328350000000008,"normal":0.8967164999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-31T12:00:10+00:00","arrival_time":"2026-01-31T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8967164999999999,"event_time":"2026-01-31T12:00:12+00:00","arrival_time":"2026-01-31T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10328350000000008,"normal":0.8967164999999999},"reference_distribution":{"anomalous":0.10328350000000008,"normal":0.8967164999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-31T12:00:12+00:00","arrival_time":"2026-01-31T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8893450621276717,"event_time":"2026-01-31T12:00:20+00:00","arrival_time":"2026-01-31T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10328350000000008,"normal":0.8967164999999999},"reference_distribution":{"anomalous":0.1106549378723283,"normal":0.8893450621276717}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-030-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-31T12:00:20+00:00","arrival_time":"2026-01-31T12:00:37+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":30,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"14f30a39a8024fab48d6dc12bf0e1dd69d2fe9fc81d947300af1c54045cfd119"}}
{"id":"evaluation-v1-belief_preservation-20260725-031","name":"Evaluation v1.0 trajectory: belief_preservation case 031","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-031","label":"Distractor 031","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.924575,"modality":"semantic_status","timestamp":"2026-02-01T12:00:10Z","metadata":{"arrival_time":"2026-02-01T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53434,"modality":"semantic_status","timestamp":"2026-02-01T12:00:20Z","metadata":{"arrival_time":"2026-02-01T12:00:38+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-031","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.71,"modality":"semantic_status","timestamp":"2026-02-01T12:00:13Z","metadata":{"arrival_time":"2026-02-01T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-01T12:00:10+00:00","obs-2":"2026-02-01T12:00:20+00:00","obs-distractor":"2026-02-01T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-01T12:00:10+00:00","obs-2":"2026-02-01T12:00:38+00:00","obs-distractor":"2026-02-01T12:00:13+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.942,"edge-ai-1":0.575},"confidence":{"obs-1":0.924575,"obs-2":0.53434,"obs-distractor":0.71},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-031-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8560949575941321,"event_time":"2026-02-01T12:00:20+00:00","arrival_time":"2026-02-01T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.13444092500000004,"normal":0.865559075},"reference_distribution":{"anomalous":0.14390504240586788,"normal":0.8560949575941321}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.865559075,"event_time":"2026-02-01T12:00:10+00:00","arrival_time":"2026-02-01T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.13444092500000004,"normal":0.865559075}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-01T12:00:10+00:00","arrival_time":"2026-02-01T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.865559075,"event_time":"2026-02-01T12:00:13+00:00","arrival_time":"2026-02-01T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.13444092500000004,"normal":0.865559075},"reference_distribution":{"anomalous":0.13444092500000004,"normal":0.865559075}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-01T12:00:13+00:00","arrival_time":"2026-02-01T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8560949575941321,"event_time":"2026-02-01T12:00:20+00:00","arrival_time":"2026-02-01T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.13444092500000004,"normal":0.865559075},"reference_distribution":{"anomalous":0.14390504240586788,"normal":0.8560949575941321}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-031-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-01T12:00:20+00:00","arrival_time":"2026-02-01T12:00:38+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":31,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"fe30f074c4fd23614884e5866052fcad34e89ac865dc2c357494957b65a813dd"}}
{"id":"evaluation-v1-belief_preservation-20260725-032","name":"Evaluation v1.0 trajectory: belief_preservation case 032","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-032","label":"Distractor 032","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9244,"modality":"semantic_status","timestamp":"2026-02-02T12:00:10Z","metadata":{"arrival_time":"2026-02-02T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53448,"modality":"semantic_status","timestamp":"2026-02-02T12:00:20Z","metadata":{"arrival_time":"2026-02-02T12:00:39+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-032","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.72,"modality":"semantic_status","timestamp":"2026-02-02T12:00:14Z","metadata":{"arrival_time":"2026-02-02T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-02T12:00:10+00:00","obs-2":"2026-02-02T12:00:20+00:00","obs-distractor":"2026-02-02T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-02T12:00:10+00:00","obs-2":"2026-02-02T12:00:39+00:00","obs-distractor":"2026-02-02T12:00:14+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.95,"edge-ai-1":0.586},"confidence":{"obs-1":0.9244,"obs-2":0.53448,"obs-distractor":0.72},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-032-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8958744714216295,"event_time":"2026-02-02T12:00:20+00:00","arrival_time":"2026-02-02T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09682000000000002,"normal":0.90318},"reference_distribution":{"anomalous":0.10412552857837051,"normal":0.8958744714216295}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.90318,"event_time":"2026-02-02T12:00:10+00:00","arrival_time":"2026-02-02T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.09682000000000002,"normal":0.90318}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-02T12:00:10+00:00","arrival_time":"2026-02-02T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.90318,"event_time":"2026-02-02T12:00:14+00:00","arrival_time":"2026-02-02T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09682000000000002,"normal":0.90318},"reference_distribution":{"anomalous":0.09682000000000002,"normal":0.90318}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-02T12:00:14+00:00","arrival_time":"2026-02-02T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8958744714216295,"event_time":"2026-02-02T12:00:20+00:00","arrival_time":"2026-02-02T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09682000000000002,"normal":0.90318},"reference_distribution":{"anomalous":0.10412552857837051,"normal":0.8958744714216295}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-032-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-02T12:00:20+00:00","arrival_time":"2026-02-02T12:00:39+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":32,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"0a68d5fec74900ec8c632bdf07a6e285b5b9756fc491d0bdc6ee77a65a21223f"}}
{"id":"evaluation-v1-belief_preservation-20260725-033","name":"Evaluation v1.0 trajectory: belief_preservation case 033","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-033","label":"Distractor 033","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.924225,"modality":"semantic_status","timestamp":"2026-02-03T12:00:10Z","metadata":{"arrival_time":"2026-02-03T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-033","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.73,"modality":"semantic_status","timestamp":"2026-02-03T12:00:12Z","metadata":{"arrival_time":"2026-02-03T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53462,"modality":"semantic_status","timestamp":"2026-02-03T12:00:20Z","metadata":{"arrival_time":"2026-02-03T12:00:40+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-02-03T12:00:10+00:00","obs-distractor":"2026-02-03T12:00:12+00:00","obs-2":"2026-02-03T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-03T12:00:10+00:00","obs-distractor":"2026-02-03T12:00:12+00:00","obs-2":"2026-02-03T12:00:40+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.958,"edge-ai-1":0.597},"confidence":{"obs-1":0.924225,"obs-distractor":0.73,"obs-2":0.53462},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-033-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8189526209052386,"event_time":"2026-02-03T12:00:20+00:00","arrival_time":"2026-02-03T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1691045,"normal":0.8308955},"reference_distribution":{"anomalous":0.18104737909476146,"normal":0.8189526209052386}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8308955,"event_time":"2026-02-03T12:00:10+00:00","arrival_time":"2026-02-03T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1691045,"normal":0.8308955}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-03T12:00:10+00:00","arrival_time":"2026-02-03T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8308955,"event_time":"2026-02-03T12:00:12+00:00","arrival_time":"2026-02-03T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1691045,"normal":0.8308955},"reference_distribution":{"anomalous":0.1691045,"normal":0.8308955}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-03T12:00:12+00:00","arrival_time":"2026-02-03T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8189526209052386,"event_time":"2026-02-03T12:00:20+00:00","arrival_time":"2026-02-03T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1691045,"normal":0.8308955},"reference_distribution":{"anomalous":0.18104737909476146,"normal":0.8189526209052386}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-033-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-03T12:00:20+00:00","arrival_time":"2026-02-03T12:00:40+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":33,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"5bdabc5c93934663617df97434d33a80c4847be768484129ea4c2983abb1133d"}}
{"id":"evaluation-v1-belief_preservation-20260725-034","name":"Evaluation v1.0 trajectory: belief_preservation case 034","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-034","label":"Distractor 034","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.92405,"modality":"semantic_status","timestamp":"2026-02-04T12:00:10Z","metadata":{"arrival_time":"2026-02-04T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-034","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.74,"modality":"semantic_status","timestamp":"2026-02-04T12:00:13Z","metadata":{"arrival_time":"2026-02-04T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53476,"modality":"semantic_status","timestamp":"2026-02-04T12:00:20Z","metadata":{"arrival_time":"2026-02-04T12:00:24+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-02-04T12:00:10+00:00","obs-distractor":"2026-02-04T12:00:13+00:00","obs-2":"2026-02-04T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-04T12:00:10+00:00","obs-distractor":"2026-02-04T12:00:13+00:00","obs-2":"2026-02-04T12:00:24+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.966,"edge-ai-1":0.608},"confidence":{"obs-1":0.92405,"obs-distractor":0.74,"obs-2":0.53476},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-034-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.9024340304491864,"event_time":"2026-02-04T12:00:20+00:00","arrival_time":"2026-02-04T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09036770000000005,"normal":0.9096323},"reference_distribution":{"anomalous":0.09756596955081372,"normal":0.9024340304491864}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9096323,"event_time":"2026-02-04T12:00:10+00:00","arrival_time":"2026-02-04T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.09036770000000005,"normal":0.9096323}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-04T12:00:10+00:00","arrival_time":"2026-02-04T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.9096323,"event_time":"2026-02-04T12:00:13+00:00","arrival_time":"2026-02-04T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09036770000000005,"normal":0.9096323},"reference_distribution":{"anomalous":0.09036770000000005,"normal":0.9096323}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-04T12:00:13+00:00","arrival_time":"2026-02-04T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.9024340304491864,"event_time":"2026-02-04T12:00:20+00:00","arrival_time":"2026-02-04T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09036770000000005,"normal":0.9096323},"reference_distribution":{"anomalous":0.09756596955081372,"normal":0.9024340304491864}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-034-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-04T12:00:20+00:00","arrival_time":"2026-02-04T12:00:24+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":34,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"9ad9e2e19ad47f91d0d03c4f649d8dd824b54056dddb579b2202c5266ba6bd9b"}}
{"id":"evaluation-v1-belief_preservation-20260725-035","name":"Evaluation v1.0 trajectory: belief_preservation case 035","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-035","label":"Distractor 035","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.923875,"modality":"semantic_status","timestamp":"2026-02-05T12:00:10Z","metadata":{"arrival_time":"2026-02-05T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-035","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.75,"modality":"semantic_status","timestamp":"2026-02-05T12:00:14Z","metadata":{"arrival_time":"2026-02-05T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.5349,"modality":"semantic_status","timestamp":"2026-02-05T12:00:20Z","metadata":{"arrival_time":"2026-02-05T12:00:25+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-02-05T12:00:10+00:00","obs-distractor":"2026-02-05T12:00:14+00:00","obs-2":"2026-02-05T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-05T12:00:10+00:00","obs-distractor":"2026-02-05T12:00:14+00:00","obs-2":"2026-02-05T12:00:25+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.974,"edge-ai-1":0.619},"confidence":{"obs-1":0.923875,"obs-distractor":0.75,"obs-2":0.5349},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-035-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8261832209242698,"event_time":"2026-02-05T12:00:20+00:00","arrival_time":"2026-02-05T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.16174774999999997,"normal":0.83825225},"reference_distribution":{"anomalous":0.17381677907573018,"normal":0.8261832209242698}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.83825225,"event_time":"2026-02-05T12:00:10+00:00","arrival_time":"2026-02-05T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.16174774999999997,"normal":0.83825225}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-05T12:00:10+00:00","arrival_time":"2026-02-05T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.83825225,"event_time":"2026-02-05T12:00:14+00:00","arrival_time":"2026-02-05T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.16174774999999997,"normal":0.83825225},"reference_distribution":{"anomalous":0.16174774999999997,"normal":0.83825225}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-05T12:00:14+00:00","arrival_time":"2026-02-05T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8261832209242698,"event_time":"2026-02-05T12:00:20+00:00","arrival_time":"2026-02-05T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.16174774999999997,"normal":0.83825225},"reference_distribution":{"anomalous":0.17381677907573018,"normal":0.8261832209242698}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-035-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-05T12:00:20+00:00","arrival_time":"2026-02-05T12:00:25+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":35,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"7fed00a4ef6680446fc6ec50682a91f5f5962c9630b8e8a691f9ebcf53394444"}}
{"id":"evaluation-v1-belief_preservation-20260725-036","name":"Evaluation v1.0 trajectory: belief_preservation case 036","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-036","label":"Distractor 036","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9237,"modality":"semantic_status","timestamp":"2026-02-06T12:00:10Z","metadata":{"arrival_time":"2026-02-06T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-036","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.76,"modality":"semantic_status","timestamp":"2026-02-06T12:00:12Z","metadata":{"arrival_time":"2026-02-06T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53504,"modality":"semantic_status","timestamp":"2026-02-06T12:00:20Z","metadata":{"arrival_time":"2026-02-06T12:00:26+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-02-06T12:00:10+00:00","obs-distractor":"2026-02-06T12:00:12+00:00","obs-2":"2026-02-06T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-06T12:00:10+00:00","obs-distractor":"2026-02-06T12:00:12+00:00","obs-2":"2026-02-06T12:00:26+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.91,"edge-ai-1":0.63},"confidence":{"obs-1":0.9237,"obs-distractor":0.76,"obs-2":0.53504},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-036-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8763033775874378,"event_time":"2026-02-06T12:00:20+00:00","arrival_time":"2026-02-06T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.114433,"normal":0.885567},"reference_distribution":{"anomalous":0.12369662241256209,"normal":0.8763033775874378}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.885567,"event_time":"2026-02-06T12:00:10+00:00","arrival_time":"2026-02-06T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.114433,"normal":0.885567}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-06T12:00:10+00:00","arrival_time":"2026-02-06T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.885567,"event_time":"2026-02-06T12:00:12+00:00","arrival_time":"2026-02-06T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.114433,"normal":0.885567},"reference_distribution":{"anomalous":0.114433,"normal":0.885567}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-06T12:00:12+00:00","arrival_time":"2026-02-06T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8763033775874378,"event_time":"2026-02-06T12:00:20+00:00","arrival_time":"2026-02-06T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.114433,"normal":0.885567},"reference_distribution":{"anomalous":0.12369662241256209,"normal":0.8763033775874378}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-036-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-06T12:00:20+00:00","arrival_time":"2026-02-06T12:00:26+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":36,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c75291b613c41ad8adf044992cf86e3b100ed81b349c3fe4aaa8988a20493f89"}}
{"id":"evaluation-v1-belief_preservation-20260725-037","name":"Evaluation v1.0 trajectory: belief_preservation case 037","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-037","label":"Distractor 037","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.923525,"modality":"semantic_status","timestamp":"2026-02-07T12:00:10Z","metadata":{"arrival_time":"2026-02-07T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53518,"modality":"semantic_status","timestamp":"2026-02-07T12:00:20Z","metadata":{"arrival_time":"2026-02-07T12:00:27+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-037","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.77,"modality":"semantic_status","timestamp":"2026-02-07T12:00:13Z","metadata":{"arrival_time":"2026-02-07T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-07T12:00:10+00:00","obs-2":"2026-02-07T12:00:20+00:00","obs-distractor":"2026-02-07T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-07T12:00:10+00:00","obs-2":"2026-02-07T12:00:27+00:00","obs-distractor":"2026-02-07T12:00:13+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.918,"edge-ai-1":0.641},"confidence":{"obs-1":0.923525,"obs-2":0.53518,"obs-distractor":0.77},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-037-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8334404665606155,"event_time":"2026-02-07T12:00:20+00:00","arrival_time":"2026-02-07T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15440359999999997,"normal":0.8455964},"reference_distribution":{"anomalous":0.1665595334393844,"normal":0.8334404665606155}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8455964,"event_time":"2026-02-07T12:00:10+00:00","arrival_time":"2026-02-07T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.15440359999999997,"normal":0.8455964}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-07T12:00:10+00:00","arrival_time":"2026-02-07T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8455964,"event_time":"2026-02-07T12:00:13+00:00","arrival_time":"2026-02-07T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15440359999999997,"normal":0.8455964},"reference_distribution":{"anomalous":0.15440359999999997,"normal":0.8455964}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-07T12:00:13+00:00","arrival_time":"2026-02-07T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8334404665606155,"event_time":"2026-02-07T12:00:20+00:00","arrival_time":"2026-02-07T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15440359999999997,"normal":0.8455964},"reference_distribution":{"anomalous":0.1665595334393844,"normal":0.8334404665606155}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-037-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-07T12:00:20+00:00","arrival_time":"2026-02-07T12:00:27+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":37,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"4f673aa8aec5a52476c93c16a0170a63307059617a0849b66bf8afd1c030be66"}}
{"id":"evaluation-v1-belief_preservation-20260725-038","name":"Evaluation v1.0 trajectory: belief_preservation case 038","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-038","label":"Distractor 038","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.92335,"modality":"semantic_status","timestamp":"2026-02-08T12:00:10Z","metadata":{"arrival_time":"2026-02-08T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-038","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.78,"modality":"semantic_status","timestamp":"2026-02-08T12:00:14Z","metadata":{"arrival_time":"2026-02-08T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53532,"modality":"semantic_status","timestamp":"2026-02-08T12:00:20Z","metadata":{"arrival_time":"2026-02-08T12:00:28+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-02-08T12:00:10+00:00","obs-distractor":"2026-02-08T12:00:14+00:00","obs-2":"2026-02-08T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-08T12:00:10+00:00","obs-distractor":"2026-02-08T12:00:14+00:00","obs-2":"2026-02-08T12:00:28+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.926,"edge-ai-1":0.652},"confidence":{"obs-1":0.92335,"obs-distractor":0.78,"obs-2":0.53532},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-038-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8828173558115042,"event_time":"2026-02-08T12:00:20+00:00","arrival_time":"2026-02-08T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10797789999999996,"normal":0.8920221},"reference_distribution":{"anomalous":0.1171826441884958,"normal":0.8828173558115042}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8920221,"event_time":"2026-02-08T12:00:10+00:00","arrival_time":"2026-02-08T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10797789999999996,"normal":0.8920221}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-08T12:00:10+00:00","arrival_time":"2026-02-08T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8920221,"event_time":"2026-02-08T12:00:14+00:00","arrival_time":"2026-02-08T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10797789999999996,"normal":0.8920221},"reference_distribution":{"anomalous":0.10797789999999996,"normal":0.8920221}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-08T12:00:14+00:00","arrival_time":"2026-02-08T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8828173558115042,"event_time":"2026-02-08T12:00:20+00:00","arrival_time":"2026-02-08T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10797789999999996,"normal":0.8920221},"reference_distribution":{"anomalous":0.1171826441884958,"normal":0.8828173558115042}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-038-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-08T12:00:20+00:00","arrival_time":"2026-02-08T12:00:28+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":38,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"26cded6b88e603051c42002539f41b1b40aefdc605685bdb115f013e8a80bf5c"}}
{"id":"evaluation-v1-belief_preservation-20260725-039","name":"Evaluation v1.0 trajectory: belief_preservation case 039","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-039","label":"Distractor 039","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.923175,"modality":"semantic_status","timestamp":"2026-02-09T12:00:10Z","metadata":{"arrival_time":"2026-02-09T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53546,"modality":"semantic_status","timestamp":"2026-02-09T12:00:20Z","metadata":{"arrival_time":"2026-02-09T12:00:29+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-039","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.79,"modality":"semantic_status","timestamp":"2026-02-09T12:00:12Z","metadata":{"arrival_time":"2026-02-09T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-09T12:00:10+00:00","obs-2":"2026-02-09T12:00:20+00:00","obs-distractor":"2026-02-09T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-09T12:00:10+00:00","obs-2":"2026-02-09T12:00:29+00:00","obs-distractor":"2026-02-09T12:00:12+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.934,"edge-ai-1":0.52},"confidence":{"obs-1":0.923175,"obs-2":0.53546,"obs-distractor":0.79},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-039-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8434284805308615,"event_time":"2026-02-09T12:00:20+00:00","arrival_time":"2026-02-09T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.14707205,"normal":0.85292795},"reference_distribution":{"anomalous":0.15657151946913853,"normal":0.8434284805308615}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.85292795,"event_time":"2026-02-09T12:00:10+00:00","arrival_time":"2026-02-09T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.14707205,"normal":0.85292795}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-09T12:00:10+00:00","arrival_time":"2026-02-09T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.85292795,"event_time":"2026-02-09T12:00:12+00:00","arrival_time":"2026-02-09T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.14707205,"normal":0.85292795},"reference_distribution":{"anomalous":0.14707205,"normal":0.85292795}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-09T12:00:12+00:00","arrival_time":"2026-02-09T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8434284805308615,"event_time":"2026-02-09T12:00:20+00:00","arrival_time":"2026-02-09T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.14707205,"normal":0.85292795},"reference_distribution":{"anomalous":0.15657151946913853,"normal":0.8434284805308615}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-039-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-09T12:00:20+00:00","arrival_time":"2026-02-09T12:00:29+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":39,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"9de658aa9e577c8c9c56dc6faae0e0ff0b5aa29bd197a9d4a858c042acd8262c"}}
{"id":"evaluation-v1-belief_preservation-20260725-040","name":"Evaluation v1.0 trajectory: belief_preservation case 040","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-040","label":"Distractor 040","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.923,"modality":"semantic_status","timestamp":"2026-02-10T12:00:10Z","metadata":{"arrival_time":"2026-02-10T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-040","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-02-10T12:00:13Z","metadata":{"arrival_time":"2026-02-10T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.5356,"modality":"semantic_status","timestamp":"2026-02-10T12:00:20Z","metadata":{"arrival_time":"2026-02-10T12:00:30+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-02-10T12:00:10+00:00","obs-distractor":"2026-02-10T12:00:13+00:00","obs-2":"2026-02-10T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-10T12:00:10+00:00","obs-distractor":"2026-02-10T12:00:13+00:00","obs-2":"2026-02-10T12:00:30+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.942,"edge-ai-1":0.531},"confidence":{"obs-1":0.923,"obs-distractor":0.6,"obs-2":0.5356},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-040-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.891353798977504,"event_time":"2026-02-10T12:00:20+00:00","arrival_time":"2026-02-10T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10153400000000001,"normal":0.898466},"reference_distribution":{"anomalous":0.108646201022496,"normal":0.891353798977504}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.898466,"event_time":"2026-02-10T12:00:10+00:00","arrival_time":"2026-02-10T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10153400000000001,"normal":0.898466}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-10T12:00:10+00:00","arrival_time":"2026-02-10T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.898466,"event_time":"2026-02-10T12:00:13+00:00","arrival_time":"2026-02-10T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10153400000000001,"normal":0.898466},"reference_distribution":{"anomalous":0.10153400000000001,"normal":0.898466}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-10T12:00:13+00:00","arrival_time":"2026-02-10T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.891353798977504,"event_time":"2026-02-10T12:00:20+00:00","arrival_time":"2026-02-10T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10153400000000001,"normal":0.898466},"reference_distribution":{"anomalous":0.108646201022496,"normal":0.891353798977504}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-040-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-10T12:00:20+00:00","arrival_time":"2026-02-10T12:00:30+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":40,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"4978899ea953474b638ba0e58782f3b406f08347117fcefdd72134fdb6dd514c"}}
{"id":"evaluation-v1-belief_preservation-20260725-041","name":"Evaluation v1.0 trajectory: belief_preservation case 041","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-041","label":"Distractor 041","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.922825,"modality":"semantic_status","timestamp":"2026-02-11T12:00:10Z","metadata":{"arrival_time":"2026-02-11T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53574,"modality":"semantic_status","timestamp":"2026-02-11T12:00:20Z","metadata":{"arrival_time":"2026-02-11T12:00:31+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-041","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-02-11T12:00:14Z","metadata":{"arrival_time":"2026-02-11T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-11T12:00:10+00:00","obs-2":"2026-02-11T12:00:20+00:00","obs-distractor":"2026-02-11T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-11T12:00:10+00:00","obs-2":"2026-02-11T12:00:31+00:00","obs-distractor":"2026-02-11T12:00:14+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.95,"edge-ai-1":0.542},"confidence":{"obs-1":0.922825,"obs-2":0.53574,"obs-distractor":0.61},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-041-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8506640768267719,"event_time":"2026-02-11T12:00:20+00:00","arrival_time":"2026-02-11T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.13975310000000007,"normal":0.8602468999999999},"reference_distribution":{"anomalous":0.14933592317322802,"normal":0.8506640768267719}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8602468999999999,"event_time":"2026-02-11T12:00:10+00:00","arrival_time":"2026-02-11T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.13975310000000007,"normal":0.8602468999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-11T12:00:10+00:00","arrival_time":"2026-02-11T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8602468999999999,"event_time":"2026-02-11T12:00:14+00:00","arrival_time":"2026-02-11T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.13975310000000007,"normal":0.8602468999999999},"reference_distribution":{"anomalous":0.13975310000000007,"normal":0.8602468999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-11T12:00:14+00:00","arrival_time":"2026-02-11T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8506640768267719,"event_time":"2026-02-11T12:00:20+00:00","arrival_time":"2026-02-11T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.13975310000000007,"normal":0.8602468999999999},"reference_distribution":{"anomalous":0.14933592317322802,"normal":0.8506640768267719}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-041-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-11T12:00:20+00:00","arrival_time":"2026-02-11T12:00:31+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":41,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"087b1bf9490894e9151832a7c41559819cb0a7060ef2c7db73e316e5ba44f517"}}
{"id":"evaluation-v1-belief_preservation-20260725-042","name":"Evaluation v1.0 trajectory: belief_preservation case 042","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-042","label":"Distractor 042","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.92265,"modality":"semantic_status","timestamp":"2026-02-12T12:00:10Z","metadata":{"arrival_time":"2026-02-12T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53588,"modality":"semantic_status","timestamp":"2026-02-12T12:00:20Z","metadata":{"arrival_time":"2026-02-12T12:00:32+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-042","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-02-12T12:00:12Z","metadata":{"arrival_time":"2026-02-12T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-12T12:00:10+00:00","obs-2":"2026-02-12T12:00:20+00:00","obs-distractor":"2026-02-12T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-12T12:00:10+00:00","obs-2":"2026-02-12T12:00:32+00:00","obs-distractor":"2026-02-12T12:00:12+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.958,"edge-ai-1":0.553},"confidence":{"obs-1":0.92265,"obs-2":0.53588,"obs-distractor":0.62},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-042-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8978418745249809,"event_time":"2026-02-12T12:00:20+00:00","arrival_time":"2026-02-12T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09510130000000006,"normal":0.9048987},"reference_distribution":{"anomalous":0.10215812547501911,"normal":0.8978418745249809}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9048987,"event_time":"2026-02-12T12:00:10+00:00","arrival_time":"2026-02-12T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.09510130000000006,"normal":0.9048987}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-12T12:00:10+00:00","arrival_time":"2026-02-12T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.9048987,"event_time":"2026-02-12T12:00:12+00:00","arrival_time":"2026-02-12T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09510130000000006,"normal":0.9048987},"reference_distribution":{"anomalous":0.09510130000000006,"normal":0.9048987}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-12T12:00:12+00:00","arrival_time":"2026-02-12T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8978418745249809,"event_time":"2026-02-12T12:00:20+00:00","arrival_time":"2026-02-12T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.09510130000000006,"normal":0.9048987},"reference_distribution":{"anomalous":0.10215812547501911,"normal":0.8978418745249809}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-042-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-12T12:00:20+00:00","arrival_time":"2026-02-12T12:00:32+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":42,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"d87104aef6ce27a2c719e0536d31b1e082a4450acf54a25203206dc3d9343851"}}
{"id":"evaluation-v1-belief_preservation-20260725-043","name":"Evaluation v1.0 trajectory: belief_preservation case 043","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-043","label":"Distractor 043","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.922475,"modality":"semantic_status","timestamp":"2026-02-13T12:00:10Z","metadata":{"arrival_time":"2026-02-13T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-043","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-02-13T12:00:13Z","metadata":{"arrival_time":"2026-02-13T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53602,"modality":"semantic_status","timestamp":"2026-02-13T12:00:20Z","metadata":{"arrival_time":"2026-02-13T12:00:33+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-02-13T12:00:10+00:00","obs-distractor":"2026-02-13T12:00:13+00:00","obs-2":"2026-02-13T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-13T12:00:10+00:00","obs-distractor":"2026-02-13T12:00:13+00:00","obs-2":"2026-02-13T12:00:33+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.966,"edge-ai-1":0.564},"confidence":{"obs-1":0.922475,"obs-distractor":0.63,"obs-2":0.53602},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-043-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8579285029143092,"event_time":"2026-02-13T12:00:20+00:00","arrival_time":"2026-02-13T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.13244674999999995,"normal":0.86755325},"reference_distribution":{"anomalous":0.14207149708569083,"normal":0.8579285029143092}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.86755325,"event_time":"2026-02-13T12:00:10+00:00","arrival_time":"2026-02-13T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.13244674999999995,"normal":0.86755325}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-13T12:00:10+00:00","arrival_time":"2026-02-13T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.86755325,"event_time":"2026-02-13T12:00:13+00:00","arrival_time":"2026-02-13T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.13244674999999995,"normal":0.86755325},"reference_distribution":{"anomalous":0.13244674999999995,"normal":0.86755325}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-13T12:00:13+00:00","arrival_time":"2026-02-13T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8579285029143092,"event_time":"2026-02-13T12:00:20+00:00","arrival_time":"2026-02-13T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.13244674999999995,"normal":0.86755325},"reference_distribution":{"anomalous":0.14207149708569083,"normal":0.8579285029143092}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-043-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-13T12:00:20+00:00","arrival_time":"2026-02-13T12:00:33+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":43,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"1590eff7e8dbcda3450dba260ef25863402011c765b7b4a49513f6dc35a32c3b"}}
{"id":"evaluation-v1-belief_preservation-20260725-044","name":"Evaluation v1.0 trajectory: belief_preservation case 044","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-044","label":"Distractor 044","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9223,"modality":"semantic_status","timestamp":"2026-02-14T12:00:10Z","metadata":{"arrival_time":"2026-02-14T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53616,"modality":"semantic_status","timestamp":"2026-02-14T12:00:20Z","metadata":{"arrival_time":"2026-02-14T12:00:34+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-044","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-02-14T12:00:14Z","metadata":{"arrival_time":"2026-02-14T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-14T12:00:10+00:00","obs-2":"2026-02-14T12:00:20+00:00","obs-distractor":"2026-02-14T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-14T12:00:10+00:00","obs-2":"2026-02-14T12:00:34+00:00","obs-distractor":"2026-02-14T12:00:14+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.974,"edge-ai-1":0.575},"confidence":{"obs-1":0.9223,"obs-2":0.53616,"obs-distractor":0.64},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-044-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.9043608502822688,"event_time":"2026-02-14T12:00:20+00:00","arrival_time":"2026-02-14T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.08867979999999998,"normal":0.9113202},"reference_distribution":{"anomalous":0.0956391497177312,"normal":0.9043608502822688}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9113202,"event_time":"2026-02-14T12:00:10+00:00","arrival_time":"2026-02-14T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.08867979999999998,"normal":0.9113202}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-14T12:00:10+00:00","arrival_time":"2026-02-14T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.9113202,"event_time":"2026-02-14T12:00:14+00:00","arrival_time":"2026-02-14T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.08867979999999998,"normal":0.9113202},"reference_distribution":{"anomalous":0.08867979999999998,"normal":0.9113202}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-14T12:00:14+00:00","arrival_time":"2026-02-14T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.9043608502822688,"event_time":"2026-02-14T12:00:20+00:00","arrival_time":"2026-02-14T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.08867979999999998,"normal":0.9113202},"reference_distribution":{"anomalous":0.0956391497177312,"normal":0.9043608502822688}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-044-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-14T12:00:20+00:00","arrival_time":"2026-02-14T12:00:34+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":44,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"f7625e18c42bf3897194b8acf4c9f7b72455ad8d9de1a1b1491ff07a5ba0cbfd"}}
{"id":"evaluation-v1-belief_preservation-20260725-045","name":"Evaluation v1.0 trajectory: belief_preservation case 045","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-045","label":"Distractor 045","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.922125,"modality":"semantic_status","timestamp":"2026-02-15T12:00:10Z","metadata":{"arrival_time":"2026-02-15T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-045","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-02-15T12:00:12Z","metadata":{"arrival_time":"2026-02-15T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.5363,"modality":"semantic_status","timestamp":"2026-02-15T12:00:20Z","metadata":{"arrival_time":"2026-02-15T12:00:35+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-02-15T12:00:10+00:00","obs-distractor":"2026-02-15T12:00:12+00:00","obs-2":"2026-02-15T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-15T12:00:10+00:00","obs-distractor":"2026-02-15T12:00:12+00:00","obs-2":"2026-02-15T12:00:35+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.91,"edge-ai-1":0.586},"confidence":{"obs-1":0.922125,"obs-distractor":0.65,"obs-2":0.5363},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-045-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8208781444200344,"event_time":"2026-02-15T12:00:20+00:00","arrival_time":"2026-02-15T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.166943375,"normal":0.833056625},"reference_distribution":{"anomalous":0.17912185557996563,"normal":0.8208781444200344}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.833056625,"event_time":"2026-02-15T12:00:10+00:00","arrival_time":"2026-02-15T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.166943375,"normal":0.833056625}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-15T12:00:10+00:00","arrival_time":"2026-02-15T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.833056625,"event_time":"2026-02-15T12:00:12+00:00","arrival_time":"2026-02-15T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.166943375,"normal":0.833056625},"reference_distribution":{"anomalous":0.166943375,"normal":0.833056625}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-15T12:00:12+00:00","arrival_time":"2026-02-15T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8208781444200344,"event_time":"2026-02-15T12:00:20+00:00","arrival_time":"2026-02-15T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.166943375,"normal":0.833056625},"reference_distribution":{"anomalous":0.17912185557996563,"normal":0.8208781444200344}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-045-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-15T12:00:20+00:00","arrival_time":"2026-02-15T12:00:35+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":45,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"8f5391edb4a0c2fd16f4357e37e716e582f263ad0017555db122d7da2a990c25"}}
{"id":"evaluation-v1-belief_preservation-20260725-046","name":"Evaluation v1.0 trajectory: belief_preservation case 046","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-046","label":"Distractor 046","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.92195,"modality":"semantic_status","timestamp":"2026-02-16T12:00:10Z","metadata":{"arrival_time":"2026-02-16T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53644,"modality":"semantic_status","timestamp":"2026-02-16T12:00:20Z","metadata":{"arrival_time":"2026-02-16T12:00:36+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-046","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-02-16T12:00:13Z","metadata":{"arrival_time":"2026-02-16T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-16T12:00:10+00:00","obs-2":"2026-02-16T12:00:20+00:00","obs-distractor":"2026-02-16T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-16T12:00:10+00:00","obs-2":"2026-02-16T12:00:36+00:00","obs-distractor":"2026-02-16T12:00:13+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.918,"edge-ai-1":0.597},"confidence":{"obs-1":0.92195,"obs-2":0.53644,"obs-distractor":0.66},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-046-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8783482962609073,"event_time":"2026-02-16T12:00:20+00:00","arrival_time":"2026-02-16T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.11264989999999986,"normal":0.8873501000000001},"reference_distribution":{"anomalous":0.12165170373909273,"normal":0.8783482962609073}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8873501000000001,"event_time":"2026-02-16T12:00:10+00:00","arrival_time":"2026-02-16T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11264989999999986,"normal":0.8873501000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-16T12:00:10+00:00","arrival_time":"2026-02-16T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8873501000000001,"event_time":"2026-02-16T12:00:13+00:00","arrival_time":"2026-02-16T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.11264989999999986,"normal":0.8873501000000001},"reference_distribution":{"anomalous":0.11264989999999986,"normal":0.8873501000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-16T12:00:13+00:00","arrival_time":"2026-02-16T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8783482962609073,"event_time":"2026-02-16T12:00:20+00:00","arrival_time":"2026-02-16T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.11264989999999986,"normal":0.8873501000000001},"reference_distribution":{"anomalous":0.12165170373909273,"normal":0.8783482962609073}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-046-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-16T12:00:20+00:00","arrival_time":"2026-02-16T12:00:36+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":46,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"4c86dea0e7f6b2c84bb4d8100f592e44de27fbf136658d8101759e2a727a8823"}}
{"id":"evaluation-v1-belief_preservation-20260725-047","name":"Evaluation v1.0 trajectory: belief_preservation case 047","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-047","label":"Distractor 047","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.921775,"modality":"semantic_status","timestamp":"2026-02-17T12:00:10Z","metadata":{"arrival_time":"2026-02-17T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53658,"modality":"semantic_status","timestamp":"2026-02-17T12:00:20Z","metadata":{"arrival_time":"2026-02-17T12:00:37+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-047","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-02-17T12:00:14Z","metadata":{"arrival_time":"2026-02-17T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-17T12:00:10+00:00","obs-2":"2026-02-17T12:00:20+00:00","obs-distractor":"2026-02-17T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-17T12:00:10+00:00","obs-2":"2026-02-17T12:00:37+00:00","obs-distractor":"2026-02-17T12:00:14+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.926,"edge-ai-1":0.608},"confidence":{"obs-1":0.921775,"obs-2":0.53658,"obs-distractor":0.67},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-047-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8280657478187012,"event_time":"2026-02-17T12:00:20+00:00","arrival_time":"2026-02-17T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15962757500000002,"normal":0.840372425},"reference_distribution":{"anomalous":0.17193425218129876,"normal":0.8280657478187012}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.840372425,"event_time":"2026-02-17T12:00:10+00:00","arrival_time":"2026-02-17T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.15962757500000002,"normal":0.840372425}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-17T12:00:10+00:00","arrival_time":"2026-02-17T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.840372425,"event_time":"2026-02-17T12:00:14+00:00","arrival_time":"2026-02-17T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15962757500000002,"normal":0.840372425},"reference_distribution":{"anomalous":0.15962757500000002,"normal":0.840372425}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-17T12:00:14+00:00","arrival_time":"2026-02-17T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8280657478187012,"event_time":"2026-02-17T12:00:20+00:00","arrival_time":"2026-02-17T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15962757500000002,"normal":0.840372425},"reference_distribution":{"anomalous":0.17193425218129876,"normal":0.8280657478187012}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-047-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-17T12:00:20+00:00","arrival_time":"2026-02-17T12:00:37+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":47,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"1af7db0c9bef0404b3bfa3312a3ace074136b89513a8dad2fda23e37f781fe3c"}}
{"id":"evaluation-v1-belief_preservation-20260725-048","name":"Evaluation v1.0 trajectory: belief_preservation case 048","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-048","label":"Distractor 048","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9216,"modality":"semantic_status","timestamp":"2026-02-18T12:00:10Z","metadata":{"arrival_time":"2026-02-18T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-048","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-02-18T12:00:12Z","metadata":{"arrival_time":"2026-02-18T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53672,"modality":"semantic_status","timestamp":"2026-02-18T12:00:20Z","metadata":{"arrival_time":"2026-02-18T12:00:38+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"edge-ai-1"},"event_times":{"obs-1":"2026-02-18T12:00:10+00:00","obs-distractor":"2026-02-18T12:00:12+00:00","obs-2":"2026-02-18T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-18T12:00:10+00:00","obs-distractor":"2026-02-18T12:00:12+00:00","obs-2":"2026-02-18T12:00:38+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.934,"edge-ai-1":0.619},"confidence":{"obs-1":0.9216,"obs-distractor":0.68,"obs-2":0.53672},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-048-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8848219078403388,"event_time":"2026-02-18T12:00:20+00:00","arrival_time":"2026-02-18T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10622559999999992,"normal":0.8937744000000001},"reference_distribution":{"anomalous":0.11517809215966124,"normal":0.8848219078403388}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8937744000000001,"event_time":"2026-02-18T12:00:10+00:00","arrival_time":"2026-02-18T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10622559999999992,"normal":0.8937744000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-18T12:00:10+00:00","arrival_time":"2026-02-18T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8937744000000001,"event_time":"2026-02-18T12:00:12+00:00","arrival_time":"2026-02-18T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10622559999999992,"normal":0.8937744000000001},"reference_distribution":{"anomalous":0.10622559999999992,"normal":0.8937744000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-18T12:00:12+00:00","arrival_time":"2026-02-18T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8848219078403388,"event_time":"2026-02-18T12:00:20+00:00","arrival_time":"2026-02-18T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.10622559999999992,"normal":0.8937744000000001},"reference_distribution":{"anomalous":0.11517809215966124,"normal":0.8848219078403388}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-048-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-18T12:00:20+00:00","arrival_time":"2026-02-18T12:00:38+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":48,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"e7e530731d57ed870f5b9a1e3399ff323e5718523b29c3c301db5fd6b39ccc65"}}
{"id":"evaluation-v1-belief_preservation-20260725-049","name":"Evaluation v1.0 trajectory: belief_preservation case 049","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-049","label":"Distractor 049","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.921425,"modality":"semantic_status","timestamp":"2026-02-19T12:00:10Z","metadata":{"arrival_time":"2026-02-19T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.53686,"modality":"semantic_status","timestamp":"2026-02-19T12:00:20Z","metadata":{"arrival_time":"2026-02-19T12:00:39+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-049","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-02-19T12:00:13Z","metadata":{"arrival_time":"2026-02-19T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"edge-ai-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-19T12:00:10+00:00","obs-2":"2026-02-19T12:00:20+00:00","obs-distractor":"2026-02-19T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-19T12:00:10+00:00","obs-2":"2026-02-19T12:00:39+00:00","obs-distractor":"2026-02-19T12:00:13+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.942,"edge-ai-1":0.63},"confidence":{"obs-1":0.921425,"obs-2":0.53686,"obs-distractor":0.69},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-049-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8352816158044281,"event_time":"2026-02-19T12:00:20+00:00","arrival_time":"2026-02-19T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15232437499999996,"normal":0.847675625},"reference_distribution":{"anomalous":0.16471838419557192,"normal":0.8352816158044281}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.847675625,"event_time":"2026-02-19T12:00:10+00:00","arrival_time":"2026-02-19T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.15232437499999996,"normal":0.847675625}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-19T12:00:10+00:00","arrival_time":"2026-02-19T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.847675625,"event_time":"2026-02-19T12:00:13+00:00","arrival_time":"2026-02-19T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15232437499999996,"normal":0.847675625},"reference_distribution":{"anomalous":0.15232437499999996,"normal":0.847675625}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-19T12:00:13+00:00","arrival_time":"2026-02-19T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"edge-ai-1","reference_confidence":0.8352816158044281,"event_time":"2026-02-19T12:00:20+00:00","arrival_time":"2026-02-19T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.15232437499999996,"normal":0.847675625},"reference_distribution":{"anomalous":0.16471838419557192,"normal":0.8352816158044281}}],"contradictions":[{"contradiction_id":"evaluation-v1-belief_preservation-20260725-049-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-19T12:00:20+00:00","arrival_time":"2026-02-19T12:00:39+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"belief_preservation","case_index":49,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"3908527348c0a6ccbe0bc050fa73333c2383ba8360fbe1324588bb6f003bde23"}}
{"id":"evaluation-v1-relation_association-20260725-000","name":"Evaluation v1.0 trajectory: relation_association case 000","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-000","label":"Distractor 000","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.91,"modality":"semantic_status","timestamp":"2026-01-01T12:00:10Z","metadata":{"arrival_time":"2026-01-01T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-000","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-01-01T12:00:12Z","metadata":{"arrival_time":"2026-01-01T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.91,"modality":"semantic_status","timestamp":"2026-01-01T12:00:11Z","metadata":{"arrival_time":"2026-01-01T12:00:15+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-01T12:00:10+00:00","obs-distractor":"2026-01-01T12:00:12+00:00","obs-2":"2026-01-01T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-01T12:00:10+00:00","obs-distractor":"2026-01-01T12:00:12+00:00","obs-2":"2026-01-01T12:00:15+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.91,"edge-ai-1":0.52},"confidence":{"obs-1":0.91,"obs-distractor":0.6,"obs-2":0.91},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8731,"event_time":"2026-01-01T12:00:11+00:00","arrival_time":"2026-01-01T12:00:15+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8731,"normal":0.1269},"reference_distribution":{"anomalous":0.8731,"normal":0.1269}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8731,"event_time":"2026-01-01T12:00:10+00:00","arrival_time":"2026-01-01T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8731,"normal":0.1269}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-01T12:00:10+00:00","arrival_time":"2026-01-01T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8731,"event_time":"2026-01-01T12:00:12+00:00","arrival_time":"2026-01-01T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8731,"normal":0.1269},"reference_distribution":{"anomalous":0.8731,"normal":0.1269}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-01T12:00:12+00:00","arrival_time":"2026-01-01T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8731,"event_time":"2026-01-01T12:00:11+00:00","arrival_time":"2026-01-01T12:00:15+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8731,"normal":0.1269},"reference_distribution":{"anomalous":0.8731,"normal":0.1269}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-01T12:00:11+00:00","arrival_time":"2026-01-01T12:00:15+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":0,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-000","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"97892d8b9b73f400feef5554453617afc6f0eea14b60092d7ead3c326547c4d1"}}
{"id":"evaluation-v1-relation_association-20260725-001","name":"Evaluation v1.0 trajectory: relation_association case 001","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-000","label":"Distractor 000","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.91,"modality":"semantic_status","timestamp":"2026-01-01T12:00:10Z","metadata":{"arrival_time":"2026-01-01T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-000","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-01-01T12:00:12Z","metadata":{"arrival_time":"2026-01-01T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.91,"modality":"semantic_status","timestamp":"2026-01-01T12:00:11Z","metadata":{"arrival_time":"2026-01-01T12:00:15+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-01T12:00:10+00:00","obs-distractor":"2026-01-01T12:00:12+00:00","obs-2":"2026-01-01T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-01T12:00:10+00:00","obs-distractor":"2026-01-01T12:00:12+00:00","obs-2":"2026-01-01T12:00:15+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.91,"edge-ai-1":0.52},"confidence":{"obs-1":0.91,"obs-distractor":0.6,"obs-2":0.91},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8731,"event_time":"2026-01-01T12:00:11+00:00","arrival_time":"2026-01-01T12:00:15+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1269,"normal":0.8731}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-01T12:00:10+00:00","arrival_time":"2026-01-01T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-01T12:00:10+00:00","arrival_time":"2026-01-01T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-01T12:00:12+00:00","arrival_time":"2026-01-01T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-01T12:00:12+00:00","arrival_time":"2026-01-01T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8731,"event_time":"2026-01-01T12:00:11+00:00","arrival_time":"2026-01-01T12:00:15+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1269,"normal":0.8731}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-01T12:00:11+00:00","arrival_time":"2026-01-01T12:00:15+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":1,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-000","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"4af87cc67a7c88b4fdd7ed21a4636ae1292f700340ac2ef8ce8867cf435e00d1"}}
{"id":"evaluation-v1-relation_association-20260725-002","name":"Evaluation v1.0 trajectory: relation_association case 002","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-001","label":"Distractor 001","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90986,"modality":"semantic_status","timestamp":"2026-01-02T12:00:10Z","metadata":{"arrival_time":"2026-01-02T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-001","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-01-02T12:00:13Z","metadata":{"arrival_time":"2026-01-02T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90986,"modality":"semantic_status","timestamp":"2026-01-02T12:00:11Z","metadata":{"arrival_time":"2026-01-02T12:00:16+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-02T12:00:10+00:00","obs-distractor":"2026-01-02T12:00:13+00:00","obs-2":"2026-01-02T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-02T12:00:10+00:00","obs-distractor":"2026-01-02T12:00:13+00:00","obs-2":"2026-01-02T12:00:16+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.918,"edge-ai-1":0.531},"confidence":{"obs-1":0.90986,"obs-distractor":0.61,"obs-2":0.90986},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8762514800000001,"event_time":"2026-01-02T12:00:11+00:00","arrival_time":"2026-01-02T12:00:16+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8762514800000001,"normal":0.12374851999999992},"reference_distribution":{"anomalous":0.8762514800000001,"normal":0.12374851999999992}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8762514800000001,"event_time":"2026-01-02T12:00:10+00:00","arrival_time":"2026-01-02T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8762514800000001,"normal":0.12374851999999992}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-02T12:00:10+00:00","arrival_time":"2026-01-02T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8762514800000001,"event_time":"2026-01-02T12:00:13+00:00","arrival_time":"2026-01-02T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8762514800000001,"normal":0.12374851999999992},"reference_distribution":{"anomalous":0.8762514800000001,"normal":0.12374851999999992}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-02T12:00:13+00:00","arrival_time":"2026-01-02T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8762514800000001,"event_time":"2026-01-02T12:00:11+00:00","arrival_time":"2026-01-02T12:00:16+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8762514800000001,"normal":0.12374851999999992},"reference_distribution":{"anomalous":0.8762514800000001,"normal":0.12374851999999992}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-02T12:00:11+00:00","arrival_time":"2026-01-02T12:00:16+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":2,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-001","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"e3d781d22952f98df6cc4b71bc6de2d30577b5a874d9963d422d2e399334a175"}}
{"id":"evaluation-v1-relation_association-20260725-003","name":"Evaluation v1.0 trajectory: relation_association case 003","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-001","label":"Distractor 001","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90986,"modality":"semantic_status","timestamp":"2026-01-02T12:00:10Z","metadata":{"arrival_time":"2026-01-02T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-001","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-01-02T12:00:13Z","metadata":{"arrival_time":"2026-01-02T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90986,"modality":"semantic_status","timestamp":"2026-01-02T12:00:11Z","metadata":{"arrival_time":"2026-01-02T12:00:16+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-02T12:00:10+00:00","obs-distractor":"2026-01-02T12:00:13+00:00","obs-2":"2026-01-02T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-02T12:00:10+00:00","obs-distractor":"2026-01-02T12:00:13+00:00","obs-2":"2026-01-02T12:00:16+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.918,"edge-ai-1":0.531},"confidence":{"obs-1":0.90986,"obs-distractor":0.61,"obs-2":0.90986},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8762514800000001,"event_time":"2026-01-02T12:00:11+00:00","arrival_time":"2026-01-02T12:00:16+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.12374851999999992,"normal":0.8762514800000001}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-02T12:00:10+00:00","arrival_time":"2026-01-02T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-02T12:00:10+00:00","arrival_time":"2026-01-02T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-02T12:00:13+00:00","arrival_time":"2026-01-02T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-02T12:00:13+00:00","arrival_time":"2026-01-02T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8762514800000001,"event_time":"2026-01-02T12:00:11+00:00","arrival_time":"2026-01-02T12:00:16+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.12374851999999992,"normal":0.8762514800000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-02T12:00:11+00:00","arrival_time":"2026-01-02T12:00:16+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":3,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-001","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"dd52d4fcf6bbf444f97942a1779f19c3590ceb1b256265cf2af946fac9c75092"}}
{"id":"evaluation-v1-relation_association-20260725-004","name":"Evaluation v1.0 trajectory: relation_association case 004","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-002","label":"Distractor 002","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90972,"modality":"semantic_status","timestamp":"2026-01-03T12:00:10Z","metadata":{"arrival_time":"2026-01-03T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-002","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-01-03T12:00:14Z","metadata":{"arrival_time":"2026-01-03T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90972,"modality":"semantic_status","timestamp":"2026-01-03T12:00:11Z","metadata":{"arrival_time":"2026-01-03T12:00:17+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-03T12:00:10+00:00","obs-distractor":"2026-01-03T12:00:14+00:00","obs-2":"2026-01-03T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-03T12:00:10+00:00","obs-distractor":"2026-01-03T12:00:14+00:00","obs-2":"2026-01-03T12:00:17+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.926,"edge-ai-1":0.542},"confidence":{"obs-1":0.90972,"obs-distractor":0.62,"obs-2":0.90972},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87940072,"event_time":"2026-01-03T12:00:11+00:00","arrival_time":"2026-01-03T12:00:17+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.87940072,"normal":0.12059927999999998},"reference_distribution":{"anomalous":0.87940072,"normal":0.12059927999999998}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87940072,"event_time":"2026-01-03T12:00:10+00:00","arrival_time":"2026-01-03T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.87940072,"normal":0.12059927999999998}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-03T12:00:10+00:00","arrival_time":"2026-01-03T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.87940072,"event_time":"2026-01-03T12:00:14+00:00","arrival_time":"2026-01-03T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.87940072,"normal":0.12059927999999998},"reference_distribution":{"anomalous":0.87940072,"normal":0.12059927999999998}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-03T12:00:14+00:00","arrival_time":"2026-01-03T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87940072,"event_time":"2026-01-03T12:00:11+00:00","arrival_time":"2026-01-03T12:00:17+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.87940072,"normal":0.12059927999999998},"reference_distribution":{"anomalous":0.87940072,"normal":0.12059927999999998}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-03T12:00:11+00:00","arrival_time":"2026-01-03T12:00:17+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":4,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-002","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"1f7ecdd6f066097a795f7e86b09915dffd175f720523a2afbdd114ebef558440"}}
{"id":"evaluation-v1-relation_association-20260725-005","name":"Evaluation v1.0 trajectory: relation_association case 005","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-002","label":"Distractor 002","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90972,"modality":"semantic_status","timestamp":"2026-01-03T12:00:10Z","metadata":{"arrival_time":"2026-01-03T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-002","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-01-03T12:00:14Z","metadata":{"arrival_time":"2026-01-03T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90972,"modality":"semantic_status","timestamp":"2026-01-03T12:00:11Z","metadata":{"arrival_time":"2026-01-03T12:00:17+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-03T12:00:10+00:00","obs-distractor":"2026-01-03T12:00:14+00:00","obs-2":"2026-01-03T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-03T12:00:10+00:00","obs-distractor":"2026-01-03T12:00:14+00:00","obs-2":"2026-01-03T12:00:17+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.926,"edge-ai-1":0.542},"confidence":{"obs-1":0.90972,"obs-distractor":0.62,"obs-2":0.90972},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87940072,"event_time":"2026-01-03T12:00:11+00:00","arrival_time":"2026-01-03T12:00:17+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.12059927999999998,"normal":0.87940072}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-03T12:00:10+00:00","arrival_time":"2026-01-03T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-03T12:00:10+00:00","arrival_time":"2026-01-03T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-03T12:00:14+00:00","arrival_time":"2026-01-03T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-03T12:00:14+00:00","arrival_time":"2026-01-03T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87940072,"event_time":"2026-01-03T12:00:11+00:00","arrival_time":"2026-01-03T12:00:17+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.12059927999999998,"normal":0.87940072}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-03T12:00:11+00:00","arrival_time":"2026-01-03T12:00:17+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":5,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-002","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"707af61aa5db4d0415ab48866e173a2c559cef1794309f559257862463952c66"}}
{"id":"evaluation-v1-relation_association-20260725-006","name":"Evaluation v1.0 trajectory: relation_association case 006","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-003","label":"Distractor 003","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90958,"modality":"semantic_status","timestamp":"2026-01-04T12:00:10Z","metadata":{"arrival_time":"2026-01-04T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-003","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-01-04T12:00:12Z","metadata":{"arrival_time":"2026-01-04T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90958,"modality":"semantic_status","timestamp":"2026-01-04T12:00:11Z","metadata":{"arrival_time":"2026-01-04T12:00:18+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-04T12:00:10+00:00","obs-distractor":"2026-01-04T12:00:12+00:00","obs-2":"2026-01-04T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-04T12:00:10+00:00","obs-distractor":"2026-01-04T12:00:12+00:00","obs-2":"2026-01-04T12:00:18+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.934,"edge-ai-1":0.553},"confidence":{"obs-1":0.90958,"obs-distractor":0.63,"obs-2":0.90958},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88254772,"event_time":"2026-01-04T12:00:11+00:00","arrival_time":"2026-01-04T12:00:18+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88254772,"normal":0.11745227999999996},"reference_distribution":{"anomalous":0.88254772,"normal":0.11745227999999996}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88254772,"event_time":"2026-01-04T12:00:10+00:00","arrival_time":"2026-01-04T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.88254772,"normal":0.11745227999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-04T12:00:10+00:00","arrival_time":"2026-01-04T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.88254772,"event_time":"2026-01-04T12:00:12+00:00","arrival_time":"2026-01-04T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88254772,"normal":0.11745227999999996},"reference_distribution":{"anomalous":0.88254772,"normal":0.11745227999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-04T12:00:12+00:00","arrival_time":"2026-01-04T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88254772,"event_time":"2026-01-04T12:00:11+00:00","arrival_time":"2026-01-04T12:00:18+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88254772,"normal":0.11745227999999996},"reference_distribution":{"anomalous":0.88254772,"normal":0.11745227999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-04T12:00:11+00:00","arrival_time":"2026-01-04T12:00:18+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":6,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-003","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"25eb3f1e453884eadc29333d9e46505c5c2f209fbc0f2ccba7e458f176ed45c4"}}
{"id":"evaluation-v1-relation_association-20260725-007","name":"Evaluation v1.0 trajectory: relation_association case 007","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-003","label":"Distractor 003","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90958,"modality":"semantic_status","timestamp":"2026-01-04T12:00:10Z","metadata":{"arrival_time":"2026-01-04T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-003","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-01-04T12:00:12Z","metadata":{"arrival_time":"2026-01-04T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90958,"modality":"semantic_status","timestamp":"2026-01-04T12:00:11Z","metadata":{"arrival_time":"2026-01-04T12:00:18+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-04T12:00:10+00:00","obs-distractor":"2026-01-04T12:00:12+00:00","obs-2":"2026-01-04T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-04T12:00:10+00:00","obs-distractor":"2026-01-04T12:00:12+00:00","obs-2":"2026-01-04T12:00:18+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.934,"edge-ai-1":0.553},"confidence":{"obs-1":0.90958,"obs-distractor":0.63,"obs-2":0.90958},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88254772,"event_time":"2026-01-04T12:00:11+00:00","arrival_time":"2026-01-04T12:00:18+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11745227999999996,"normal":0.88254772}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-04T12:00:10+00:00","arrival_time":"2026-01-04T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-04T12:00:10+00:00","arrival_time":"2026-01-04T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-04T12:00:12+00:00","arrival_time":"2026-01-04T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-04T12:00:12+00:00","arrival_time":"2026-01-04T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88254772,"event_time":"2026-01-04T12:00:11+00:00","arrival_time":"2026-01-04T12:00:18+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11745227999999996,"normal":0.88254772}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-04T12:00:11+00:00","arrival_time":"2026-01-04T12:00:18+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":7,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-003","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"9de81ee3a75128b626f884e4bed30f9119e267f612a544347cc5fde74075b3ed"}}
{"id":"evaluation-v1-relation_association-20260725-008","name":"Evaluation v1.0 trajectory: relation_association case 008","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-004","label":"Distractor 004","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90944,"modality":"semantic_status","timestamp":"2026-01-05T12:00:10Z","metadata":{"arrival_time":"2026-01-05T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90944,"modality":"semantic_status","timestamp":"2026-01-05T12:00:11Z","metadata":{"arrival_time":"2026-01-05T12:00:19+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-004","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-01-05T12:00:13Z","metadata":{"arrival_time":"2026-01-05T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-05T12:00:10+00:00","obs-2":"2026-01-05T12:00:11+00:00","obs-distractor":"2026-01-05T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-05T12:00:10+00:00","obs-2":"2026-01-05T12:00:19+00:00","obs-distractor":"2026-01-05T12:00:13+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.942,"edge-ai-1":0.564},"confidence":{"obs-1":0.90944,"obs-2":0.90944,"obs-distractor":0.64},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88569248,"event_time":"2026-01-05T12:00:11+00:00","arrival_time":"2026-01-05T12:00:19+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88569248,"normal":0.11430752},"reference_distribution":{"anomalous":0.88569248,"normal":0.11430752}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88569248,"event_time":"2026-01-05T12:00:10+00:00","arrival_time":"2026-01-05T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.88569248,"normal":0.11430752}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-05T12:00:10+00:00","arrival_time":"2026-01-05T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.88569248,"event_time":"2026-01-05T12:00:13+00:00","arrival_time":"2026-01-05T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88569248,"normal":0.11430752},"reference_distribution":{"anomalous":0.88569248,"normal":0.11430752}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-05T12:00:13+00:00","arrival_time":"2026-01-05T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88569248,"event_time":"2026-01-05T12:00:11+00:00","arrival_time":"2026-01-05T12:00:19+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88569248,"normal":0.11430752},"reference_distribution":{"anomalous":0.88569248,"normal":0.11430752}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-05T12:00:11+00:00","arrival_time":"2026-01-05T12:00:19+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":8,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-004","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"8fee71299a3ef86580051800caf396e617f825f0fb63538f2c910fd18be37168"}}
{"id":"evaluation-v1-relation_association-20260725-009","name":"Evaluation v1.0 trajectory: relation_association case 009","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-004","label":"Distractor 004","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90944,"modality":"semantic_status","timestamp":"2026-01-05T12:00:10Z","metadata":{"arrival_time":"2026-01-05T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90944,"modality":"semantic_status","timestamp":"2026-01-05T12:00:11Z","metadata":{"arrival_time":"2026-01-05T12:00:19+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-004","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-01-05T12:00:13Z","metadata":{"arrival_time":"2026-01-05T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-05T12:00:10+00:00","obs-2":"2026-01-05T12:00:11+00:00","obs-distractor":"2026-01-05T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-05T12:00:10+00:00","obs-2":"2026-01-05T12:00:19+00:00","obs-distractor":"2026-01-05T12:00:13+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.942,"edge-ai-1":0.564},"confidence":{"obs-1":0.90944,"obs-2":0.90944,"obs-distractor":0.64},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88569248,"event_time":"2026-01-05T12:00:11+00:00","arrival_time":"2026-01-05T12:00:19+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11430752,"normal":0.88569248}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-05T12:00:10+00:00","arrival_time":"2026-01-05T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-05T12:00:10+00:00","arrival_time":"2026-01-05T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-05T12:00:13+00:00","arrival_time":"2026-01-05T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-05T12:00:13+00:00","arrival_time":"2026-01-05T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88569248,"event_time":"2026-01-05T12:00:11+00:00","arrival_time":"2026-01-05T12:00:19+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11430752,"normal":0.88569248}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-05T12:00:11+00:00","arrival_time":"2026-01-05T12:00:19+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":9,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-004","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"5e82fad1d7d6cadd54d1243eb9404bb7625e6e46185386287a0b303231b63d47"}}
{"id":"evaluation-v1-relation_association-20260725-010","name":"Evaluation v1.0 trajectory: relation_association case 010","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-005","label":"Distractor 005","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.9093,"modality":"semantic_status","timestamp":"2026-01-06T12:00:10Z","metadata":{"arrival_time":"2026-01-06T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.9093,"modality":"semantic_status","timestamp":"2026-01-06T12:00:11Z","metadata":{"arrival_time":"2026-01-06T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-005","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-01-06T12:00:14Z","metadata":{"arrival_time":"2026-01-06T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-06T12:00:10+00:00","obs-2":"2026-01-06T12:00:11+00:00","obs-distractor":"2026-01-06T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-06T12:00:10+00:00","obs-2":"2026-01-06T12:00:20+00:00","obs-distractor":"2026-01-06T12:00:14+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.95,"edge-ai-1":0.575},"confidence":{"obs-1":0.9093,"obs-2":0.9093,"obs-distractor":0.65},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.888835,"event_time":"2026-01-06T12:00:11+00:00","arrival_time":"2026-01-06T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.888835,"normal":0.11116499999999996},"reference_distribution":{"anomalous":0.888835,"normal":0.11116499999999996}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.888835,"event_time":"2026-01-06T12:00:10+00:00","arrival_time":"2026-01-06T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.888835,"normal":0.11116499999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-06T12:00:10+00:00","arrival_time":"2026-01-06T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.888835,"event_time":"2026-01-06T12:00:14+00:00","arrival_time":"2026-01-06T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.888835,"normal":0.11116499999999996},"reference_distribution":{"anomalous":0.888835,"normal":0.11116499999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-06T12:00:14+00:00","arrival_time":"2026-01-06T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.888835,"event_time":"2026-01-06T12:00:11+00:00","arrival_time":"2026-01-06T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.888835,"normal":0.11116499999999996},"reference_distribution":{"anomalous":0.888835,"normal":0.11116499999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-06T12:00:11+00:00","arrival_time":"2026-01-06T12:00:20+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":10,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-005","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"cd1b0131a1d2baa77e742a0de0fc9278fe26502e93666c35f7b895890a80d600"}}
{"id":"evaluation-v1-relation_association-20260725-011","name":"Evaluation v1.0 trajectory: relation_association case 011","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-005","label":"Distractor 005","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.9093,"modality":"semantic_status","timestamp":"2026-01-06T12:00:10Z","metadata":{"arrival_time":"2026-01-06T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.9093,"modality":"semantic_status","timestamp":"2026-01-06T12:00:11Z","metadata":{"arrival_time":"2026-01-06T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-005","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-01-06T12:00:14Z","metadata":{"arrival_time":"2026-01-06T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-06T12:00:10+00:00","obs-2":"2026-01-06T12:00:11+00:00","obs-distractor":"2026-01-06T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-06T12:00:10+00:00","obs-2":"2026-01-06T12:00:20+00:00","obs-distractor":"2026-01-06T12:00:14+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.95,"edge-ai-1":0.575},"confidence":{"obs-1":0.9093,"obs-2":0.9093,"obs-distractor":0.65},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.888835,"event_time":"2026-01-06T12:00:11+00:00","arrival_time":"2026-01-06T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11116499999999996,"normal":0.888835}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-06T12:00:10+00:00","arrival_time":"2026-01-06T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-06T12:00:10+00:00","arrival_time":"2026-01-06T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-06T12:00:14+00:00","arrival_time":"2026-01-06T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-06T12:00:14+00:00","arrival_time":"2026-01-06T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.888835,"event_time":"2026-01-06T12:00:11+00:00","arrival_time":"2026-01-06T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11116499999999996,"normal":0.888835}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-06T12:00:11+00:00","arrival_time":"2026-01-06T12:00:20+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":11,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-005","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"0e8a7a456788826f2b9beeaeb3d0209966523ea705a700456c32f7db5ddde4e1"}}
{"id":"evaluation-v1-relation_association-20260725-012","name":"Evaluation v1.0 trajectory: relation_association case 012","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-006","label":"Distractor 006","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90916,"modality":"semantic_status","timestamp":"2026-01-07T12:00:10Z","metadata":{"arrival_time":"2026-01-07T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90916,"modality":"semantic_status","timestamp":"2026-01-07T12:00:11Z","metadata":{"arrival_time":"2026-01-07T12:00:21+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-006","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-01-07T12:00:12Z","metadata":{"arrival_time":"2026-01-07T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-07T12:00:10+00:00","obs-2":"2026-01-07T12:00:11+00:00","obs-distractor":"2026-01-07T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-07T12:00:10+00:00","obs-2":"2026-01-07T12:00:21+00:00","obs-distractor":"2026-01-07T12:00:12+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.958,"edge-ai-1":0.586},"confidence":{"obs-1":0.90916,"obs-2":0.90916,"obs-distractor":0.66},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.89197528,"event_time":"2026-01-07T12:00:11+00:00","arrival_time":"2026-01-07T12:00:21+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.89197528,"normal":0.10802471999999996},"reference_distribution":{"anomalous":0.89197528,"normal":0.10802471999999996}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.89197528,"event_time":"2026-01-07T12:00:10+00:00","arrival_time":"2026-01-07T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.89197528,"normal":0.10802471999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-07T12:00:10+00:00","arrival_time":"2026-01-07T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.89197528,"event_time":"2026-01-07T12:00:12+00:00","arrival_time":"2026-01-07T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.89197528,"normal":0.10802471999999996},"reference_distribution":{"anomalous":0.89197528,"normal":0.10802471999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-07T12:00:12+00:00","arrival_time":"2026-01-07T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.89197528,"event_time":"2026-01-07T12:00:11+00:00","arrival_time":"2026-01-07T12:00:21+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.89197528,"normal":0.10802471999999996},"reference_distribution":{"anomalous":0.89197528,"normal":0.10802471999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-07T12:00:11+00:00","arrival_time":"2026-01-07T12:00:21+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":12,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-006","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c9214b3a8b7cab83bf828b2ae3e5046856d608db00685a33e774c904c2954162"}}
{"id":"evaluation-v1-relation_association-20260725-013","name":"Evaluation v1.0 trajectory: relation_association case 013","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-006","label":"Distractor 006","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90916,"modality":"semantic_status","timestamp":"2026-01-07T12:00:10Z","metadata":{"arrival_time":"2026-01-07T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90916,"modality":"semantic_status","timestamp":"2026-01-07T12:00:11Z","metadata":{"arrival_time":"2026-01-07T12:00:21+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-006","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-01-07T12:00:12Z","metadata":{"arrival_time":"2026-01-07T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-07T12:00:10+00:00","obs-2":"2026-01-07T12:00:11+00:00","obs-distractor":"2026-01-07T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-07T12:00:10+00:00","obs-2":"2026-01-07T12:00:21+00:00","obs-distractor":"2026-01-07T12:00:12+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.958,"edge-ai-1":0.586},"confidence":{"obs-1":0.90916,"obs-2":0.90916,"obs-distractor":0.66},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.89197528,"event_time":"2026-01-07T12:00:11+00:00","arrival_time":"2026-01-07T12:00:21+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10802471999999996,"normal":0.89197528}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-07T12:00:10+00:00","arrival_time":"2026-01-07T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-07T12:00:10+00:00","arrival_time":"2026-01-07T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-07T12:00:12+00:00","arrival_time":"2026-01-07T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-07T12:00:12+00:00","arrival_time":"2026-01-07T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.89197528,"event_time":"2026-01-07T12:00:11+00:00","arrival_time":"2026-01-07T12:00:21+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10802471999999996,"normal":0.89197528}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-07T12:00:11+00:00","arrival_time":"2026-01-07T12:00:21+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":13,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-006","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"3659b4ecc575505359a2f100a6e2d86f2966d333b288b790a6b832c2821071c0"}}
{"id":"evaluation-v1-relation_association-20260725-014","name":"Evaluation v1.0 trajectory: relation_association case 014","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-007","label":"Distractor 007","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90902,"modality":"semantic_status","timestamp":"2026-01-08T12:00:10Z","metadata":{"arrival_time":"2026-01-08T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-007","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-01-08T12:00:13Z","metadata":{"arrival_time":"2026-01-08T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90902,"modality":"semantic_status","timestamp":"2026-01-08T12:00:11Z","metadata":{"arrival_time":"2026-01-08T12:00:22+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-08T12:00:10+00:00","obs-distractor":"2026-01-08T12:00:13+00:00","obs-2":"2026-01-08T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-08T12:00:10+00:00","obs-distractor":"2026-01-08T12:00:13+00:00","obs-2":"2026-01-08T12:00:22+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.966,"edge-ai-1":0.597},"confidence":{"obs-1":0.90902,"obs-distractor":0.67,"obs-2":0.90902},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8951133200000001,"event_time":"2026-01-08T12:00:11+00:00","arrival_time":"2026-01-08T12:00:22+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8951133200000001,"normal":0.1048866799999999},"reference_distribution":{"anomalous":0.8951133200000001,"normal":0.1048866799999999}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8951133200000001,"event_time":"2026-01-08T12:00:10+00:00","arrival_time":"2026-01-08T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8951133200000001,"normal":0.1048866799999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-08T12:00:10+00:00","arrival_time":"2026-01-08T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8951133200000001,"event_time":"2026-01-08T12:00:13+00:00","arrival_time":"2026-01-08T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8951133200000001,"normal":0.1048866799999999},"reference_distribution":{"anomalous":0.8951133200000001,"normal":0.1048866799999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-08T12:00:13+00:00","arrival_time":"2026-01-08T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8951133200000001,"event_time":"2026-01-08T12:00:11+00:00","arrival_time":"2026-01-08T12:00:22+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8951133200000001,"normal":0.1048866799999999},"reference_distribution":{"anomalous":0.8951133200000001,"normal":0.1048866799999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-08T12:00:11+00:00","arrival_time":"2026-01-08T12:00:22+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":14,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-007","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"de1d858618357b613ac1fcc4684aa55932566ab217949fa80eb9cc5a2f1f927e"}}
{"id":"evaluation-v1-relation_association-20260725-015","name":"Evaluation v1.0 trajectory: relation_association case 015","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-007","label":"Distractor 007","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90902,"modality":"semantic_status","timestamp":"2026-01-08T12:00:10Z","metadata":{"arrival_time":"2026-01-08T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-007","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-01-08T12:00:13Z","metadata":{"arrival_time":"2026-01-08T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90902,"modality":"semantic_status","timestamp":"2026-01-08T12:00:11Z","metadata":{"arrival_time":"2026-01-08T12:00:22+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-08T12:00:10+00:00","obs-distractor":"2026-01-08T12:00:13+00:00","obs-2":"2026-01-08T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-08T12:00:10+00:00","obs-distractor":"2026-01-08T12:00:13+00:00","obs-2":"2026-01-08T12:00:22+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.966,"edge-ai-1":0.597},"confidence":{"obs-1":0.90902,"obs-distractor":0.67,"obs-2":0.90902},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8951133200000001,"event_time":"2026-01-08T12:00:11+00:00","arrival_time":"2026-01-08T12:00:22+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1048866799999999,"normal":0.8951133200000001}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-08T12:00:10+00:00","arrival_time":"2026-01-08T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-08T12:00:10+00:00","arrival_time":"2026-01-08T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-08T12:00:13+00:00","arrival_time":"2026-01-08T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-08T12:00:13+00:00","arrival_time":"2026-01-08T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8951133200000001,"event_time":"2026-01-08T12:00:11+00:00","arrival_time":"2026-01-08T12:00:22+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1048866799999999,"normal":0.8951133200000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-08T12:00:11+00:00","arrival_time":"2026-01-08T12:00:22+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":15,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-007","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"5af66fd98b5c5ababcf43306ab40f7bf66da7b55f3a9f83e5078c7d25cdbf9fb"}}
{"id":"evaluation-v1-relation_association-20260725-016","name":"Evaluation v1.0 trajectory: relation_association case 016","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-008","label":"Distractor 008","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90888,"modality":"semantic_status","timestamp":"2026-01-09T12:00:10Z","metadata":{"arrival_time":"2026-01-09T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-008","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-01-09T12:00:14Z","metadata":{"arrival_time":"2026-01-09T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90888,"modality":"semantic_status","timestamp":"2026-01-09T12:00:11Z","metadata":{"arrival_time":"2026-01-09T12:00:23+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-09T12:00:10+00:00","obs-distractor":"2026-01-09T12:00:14+00:00","obs-2":"2026-01-09T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-09T12:00:10+00:00","obs-distractor":"2026-01-09T12:00:14+00:00","obs-2":"2026-01-09T12:00:23+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.974,"edge-ai-1":0.608},"confidence":{"obs-1":0.90888,"obs-distractor":0.68,"obs-2":0.90888},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.89824912,"event_time":"2026-01-09T12:00:11+00:00","arrival_time":"2026-01-09T12:00:23+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.89824912,"normal":0.10175087999999999},"reference_distribution":{"anomalous":0.89824912,"normal":0.10175087999999999}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.89824912,"event_time":"2026-01-09T12:00:10+00:00","arrival_time":"2026-01-09T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.89824912,"normal":0.10175087999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-09T12:00:10+00:00","arrival_time":"2026-01-09T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.89824912,"event_time":"2026-01-09T12:00:14+00:00","arrival_time":"2026-01-09T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.89824912,"normal":0.10175087999999999},"reference_distribution":{"anomalous":0.89824912,"normal":0.10175087999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-09T12:00:14+00:00","arrival_time":"2026-01-09T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.89824912,"event_time":"2026-01-09T12:00:11+00:00","arrival_time":"2026-01-09T12:00:23+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.89824912,"normal":0.10175087999999999},"reference_distribution":{"anomalous":0.89824912,"normal":0.10175087999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-09T12:00:11+00:00","arrival_time":"2026-01-09T12:00:23+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":16,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-008","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"df90cac2fcb336e67658f7d96d94ac3987dfa788a24554b8d0e536ba7adce424"}}
{"id":"evaluation-v1-relation_association-20260725-017","name":"Evaluation v1.0 trajectory: relation_association case 017","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-008","label":"Distractor 008","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90888,"modality":"semantic_status","timestamp":"2026-01-09T12:00:10Z","metadata":{"arrival_time":"2026-01-09T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-008","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-01-09T12:00:14Z","metadata":{"arrival_time":"2026-01-09T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90888,"modality":"semantic_status","timestamp":"2026-01-09T12:00:11Z","metadata":{"arrival_time":"2026-01-09T12:00:23+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-09T12:00:10+00:00","obs-distractor":"2026-01-09T12:00:14+00:00","obs-2":"2026-01-09T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-09T12:00:10+00:00","obs-distractor":"2026-01-09T12:00:14+00:00","obs-2":"2026-01-09T12:00:23+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.974,"edge-ai-1":0.608},"confidence":{"obs-1":0.90888,"obs-distractor":0.68,"obs-2":0.90888},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.89824912,"event_time":"2026-01-09T12:00:11+00:00","arrival_time":"2026-01-09T12:00:23+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10175087999999999,"normal":0.89824912}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-09T12:00:10+00:00","arrival_time":"2026-01-09T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-09T12:00:10+00:00","arrival_time":"2026-01-09T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-09T12:00:14+00:00","arrival_time":"2026-01-09T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-09T12:00:14+00:00","arrival_time":"2026-01-09T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.89824912,"event_time":"2026-01-09T12:00:11+00:00","arrival_time":"2026-01-09T12:00:23+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10175087999999999,"normal":0.89824912}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-09T12:00:11+00:00","arrival_time":"2026-01-09T12:00:23+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":17,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-008","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"fb1b131937d2b1f194846c0eda35a3e386bc2abe90d40a600ebe44cf5b9bed21"}}
{"id":"evaluation-v1-relation_association-20260725-018","name":"Evaluation v1.0 trajectory: relation_association case 018","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-009","label":"Distractor 009","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90874,"modality":"semantic_status","timestamp":"2026-01-10T12:00:10Z","metadata":{"arrival_time":"2026-01-10T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-009","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-01-10T12:00:12Z","metadata":{"arrival_time":"2026-01-10T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90874,"modality":"semantic_status","timestamp":"2026-01-10T12:00:11Z","metadata":{"arrival_time":"2026-01-10T12:00:24+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-10T12:00:10+00:00","obs-distractor":"2026-01-10T12:00:12+00:00","obs-2":"2026-01-10T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-10T12:00:10+00:00","obs-distractor":"2026-01-10T12:00:12+00:00","obs-2":"2026-01-10T12:00:24+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.91,"edge-ai-1":0.619},"confidence":{"obs-1":0.90874,"obs-distractor":0.69,"obs-2":0.90874},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8719534,"event_time":"2026-01-10T12:00:11+00:00","arrival_time":"2026-01-10T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8719534,"normal":0.1280466},"reference_distribution":{"anomalous":0.8719534,"normal":0.1280466}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8719534,"event_time":"2026-01-10T12:00:10+00:00","arrival_time":"2026-01-10T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8719534,"normal":0.1280466}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-10T12:00:10+00:00","arrival_time":"2026-01-10T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8719534,"event_time":"2026-01-10T12:00:12+00:00","arrival_time":"2026-01-10T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8719534,"normal":0.1280466},"reference_distribution":{"anomalous":0.8719534,"normal":0.1280466}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-10T12:00:12+00:00","arrival_time":"2026-01-10T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8719534,"event_time":"2026-01-10T12:00:11+00:00","arrival_time":"2026-01-10T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8719534,"normal":0.1280466},"reference_distribution":{"anomalous":0.8719534,"normal":0.1280466}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-10T12:00:11+00:00","arrival_time":"2026-01-10T12:00:24+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":18,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-009","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"6f58afef712256a6e9299d219d94708023276852f76fd2f798c833695c6d0f87"}}
{"id":"evaluation-v1-relation_association-20260725-019","name":"Evaluation v1.0 trajectory: relation_association case 019","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-009","label":"Distractor 009","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90874,"modality":"semantic_status","timestamp":"2026-01-10T12:00:10Z","metadata":{"arrival_time":"2026-01-10T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-009","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-01-10T12:00:12Z","metadata":{"arrival_time":"2026-01-10T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90874,"modality":"semantic_status","timestamp":"2026-01-10T12:00:11Z","metadata":{"arrival_time":"2026-01-10T12:00:24+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-10T12:00:10+00:00","obs-distractor":"2026-01-10T12:00:12+00:00","obs-2":"2026-01-10T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-10T12:00:10+00:00","obs-distractor":"2026-01-10T12:00:12+00:00","obs-2":"2026-01-10T12:00:24+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.91,"edge-ai-1":0.619},"confidence":{"obs-1":0.90874,"obs-distractor":0.69,"obs-2":0.90874},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8719534,"event_time":"2026-01-10T12:00:11+00:00","arrival_time":"2026-01-10T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1280466,"normal":0.8719534}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-10T12:00:10+00:00","arrival_time":"2026-01-10T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-10T12:00:10+00:00","arrival_time":"2026-01-10T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-10T12:00:12+00:00","arrival_time":"2026-01-10T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-10T12:00:12+00:00","arrival_time":"2026-01-10T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8719534,"event_time":"2026-01-10T12:00:11+00:00","arrival_time":"2026-01-10T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1280466,"normal":0.8719534}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-10T12:00:11+00:00","arrival_time":"2026-01-10T12:00:24+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":19,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-009","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"ded6b9bab99ba8db7fb22ff42ea50d183f10bd685ba95f8e69c10983d157ba52"}}
{"id":"evaluation-v1-relation_association-20260725-020","name":"Evaluation v1.0 trajectory: relation_association case 020","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-010","label":"Distractor 010","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.9086,"modality":"semantic_status","timestamp":"2026-01-11T12:00:10Z","metadata":{"arrival_time":"2026-01-11T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-010","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.7,"modality":"semantic_status","timestamp":"2026-01-11T12:00:13Z","metadata":{"arrival_time":"2026-01-11T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.9086,"modality":"semantic_status","timestamp":"2026-01-11T12:00:11Z","metadata":{"arrival_time":"2026-01-11T12:00:25+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-11T12:00:10+00:00","obs-distractor":"2026-01-11T12:00:13+00:00","obs-2":"2026-01-11T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-11T12:00:10+00:00","obs-distractor":"2026-01-11T12:00:13+00:00","obs-2":"2026-01-11T12:00:25+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.918,"edge-ai-1":0.63},"confidence":{"obs-1":0.9086,"obs-distractor":0.7,"obs-2":0.9086},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8750948000000001,"event_time":"2026-01-11T12:00:11+00:00","arrival_time":"2026-01-11T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8750948000000001,"normal":0.12490519999999994},"reference_distribution":{"anomalous":0.8750948000000001,"normal":0.12490519999999994}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8750948000000001,"event_time":"2026-01-11T12:00:10+00:00","arrival_time":"2026-01-11T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8750948000000001,"normal":0.12490519999999994}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-11T12:00:10+00:00","arrival_time":"2026-01-11T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8750948000000001,"event_time":"2026-01-11T12:00:13+00:00","arrival_time":"2026-01-11T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8750948000000001,"normal":0.12490519999999994},"reference_distribution":{"anomalous":0.8750948000000001,"normal":0.12490519999999994}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-11T12:00:13+00:00","arrival_time":"2026-01-11T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8750948000000001,"event_time":"2026-01-11T12:00:11+00:00","arrival_time":"2026-01-11T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8750948000000001,"normal":0.12490519999999994},"reference_distribution":{"anomalous":0.8750948000000001,"normal":0.12490519999999994}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-11T12:00:11+00:00","arrival_time":"2026-01-11T12:00:25+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":20,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-010","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"4f89fc15bd035a919d7ba7f5d1654ef2d66cce9f477ca56e38d57bd233466aa6"}}
{"id":"evaluation-v1-relation_association-20260725-021","name":"Evaluation v1.0 trajectory: relation_association case 021","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-010","label":"Distractor 010","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.9086,"modality":"semantic_status","timestamp":"2026-01-11T12:00:10Z","metadata":{"arrival_time":"2026-01-11T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-010","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.7,"modality":"semantic_status","timestamp":"2026-01-11T12:00:13Z","metadata":{"arrival_time":"2026-01-11T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.9086,"modality":"semantic_status","timestamp":"2026-01-11T12:00:11Z","metadata":{"arrival_time":"2026-01-11T12:00:25+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-11T12:00:10+00:00","obs-distractor":"2026-01-11T12:00:13+00:00","obs-2":"2026-01-11T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-11T12:00:10+00:00","obs-distractor":"2026-01-11T12:00:13+00:00","obs-2":"2026-01-11T12:00:25+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.918,"edge-ai-1":0.63},"confidence":{"obs-1":0.9086,"obs-distractor":0.7,"obs-2":0.9086},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8750948000000001,"event_time":"2026-01-11T12:00:11+00:00","arrival_time":"2026-01-11T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.12490519999999994,"normal":0.8750948000000001}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-11T12:00:10+00:00","arrival_time":"2026-01-11T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-11T12:00:10+00:00","arrival_time":"2026-01-11T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-11T12:00:13+00:00","arrival_time":"2026-01-11T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-11T12:00:13+00:00","arrival_time":"2026-01-11T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8750948000000001,"event_time":"2026-01-11T12:00:11+00:00","arrival_time":"2026-01-11T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.12490519999999994,"normal":0.8750948000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-11T12:00:11+00:00","arrival_time":"2026-01-11T12:00:25+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":21,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-010","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"06529b9725c5ba214dc0bbbec4070c66ac1f85367e5bea3419c7c5851958c7f1"}}
{"id":"evaluation-v1-relation_association-20260725-022","name":"Evaluation v1.0 trajectory: relation_association case 022","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-011","label":"Distractor 011","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90846,"modality":"semantic_status","timestamp":"2026-01-12T12:00:10Z","metadata":{"arrival_time":"2026-01-12T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-011","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.71,"modality":"semantic_status","timestamp":"2026-01-12T12:00:14Z","metadata":{"arrival_time":"2026-01-12T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90846,"modality":"semantic_status","timestamp":"2026-01-12T12:00:11Z","metadata":{"arrival_time":"2026-01-12T12:00:26+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-12T12:00:10+00:00","obs-distractor":"2026-01-12T12:00:14+00:00","obs-2":"2026-01-12T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-12T12:00:10+00:00","obs-distractor":"2026-01-12T12:00:14+00:00","obs-2":"2026-01-12T12:00:26+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.926,"edge-ai-1":0.641},"confidence":{"obs-1":0.90846,"obs-distractor":0.71,"obs-2":0.90846},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87823396,"event_time":"2026-01-12T12:00:11+00:00","arrival_time":"2026-01-12T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.87823396,"normal":0.12176604000000002},"reference_distribution":{"anomalous":0.87823396,"normal":0.12176604000000002}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87823396,"event_time":"2026-01-12T12:00:10+00:00","arrival_time":"2026-01-12T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.87823396,"normal":0.12176604000000002}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-12T12:00:10+00:00","arrival_time":"2026-01-12T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.87823396,"event_time":"2026-01-12T12:00:14+00:00","arrival_time":"2026-01-12T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.87823396,"normal":0.12176604000000002},"reference_distribution":{"anomalous":0.87823396,"normal":0.12176604000000002}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-12T12:00:14+00:00","arrival_time":"2026-01-12T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87823396,"event_time":"2026-01-12T12:00:11+00:00","arrival_time":"2026-01-12T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.87823396,"normal":0.12176604000000002},"reference_distribution":{"anomalous":0.87823396,"normal":0.12176604000000002}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-12T12:00:11+00:00","arrival_time":"2026-01-12T12:00:26+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":22,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-011","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"007a0d5af497145e46a13d9db3633db2ec0db25d8e0e2b936f28bf2c27f5a3ce"}}
{"id":"evaluation-v1-relation_association-20260725-023","name":"Evaluation v1.0 trajectory: relation_association case 023","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-011","label":"Distractor 011","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90846,"modality":"semantic_status","timestamp":"2026-01-12T12:00:10Z","metadata":{"arrival_time":"2026-01-12T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-011","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.71,"modality":"semantic_status","timestamp":"2026-01-12T12:00:14Z","metadata":{"arrival_time":"2026-01-12T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90846,"modality":"semantic_status","timestamp":"2026-01-12T12:00:11Z","metadata":{"arrival_time":"2026-01-12T12:00:26+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-12T12:00:10+00:00","obs-distractor":"2026-01-12T12:00:14+00:00","obs-2":"2026-01-12T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-12T12:00:10+00:00","obs-distractor":"2026-01-12T12:00:14+00:00","obs-2":"2026-01-12T12:00:26+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.926,"edge-ai-1":0.641},"confidence":{"obs-1":0.90846,"obs-distractor":0.71,"obs-2":0.90846},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87823396,"event_time":"2026-01-12T12:00:11+00:00","arrival_time":"2026-01-12T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.12176604000000002,"normal":0.87823396}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-12T12:00:10+00:00","arrival_time":"2026-01-12T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-12T12:00:10+00:00","arrival_time":"2026-01-12T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-12T12:00:14+00:00","arrival_time":"2026-01-12T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-12T12:00:14+00:00","arrival_time":"2026-01-12T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87823396,"event_time":"2026-01-12T12:00:11+00:00","arrival_time":"2026-01-12T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.12176604000000002,"normal":0.87823396}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-12T12:00:11+00:00","arrival_time":"2026-01-12T12:00:26+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":23,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-011","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"4bffacc476ebefb53fedbdd6e06e1403fd20d82568082834da46f5ed66105476"}}
{"id":"evaluation-v1-relation_association-20260725-024","name":"Evaluation v1.0 trajectory: relation_association case 024","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-012","label":"Distractor 012","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90832,"modality":"semantic_status","timestamp":"2026-01-13T12:00:10Z","metadata":{"arrival_time":"2026-01-13T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90832,"modality":"semantic_status","timestamp":"2026-01-13T12:00:11Z","metadata":{"arrival_time":"2026-01-13T12:00:27+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-012","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.72,"modality":"semantic_status","timestamp":"2026-01-13T12:00:12Z","metadata":{"arrival_time":"2026-01-13T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-13T12:00:10+00:00","obs-2":"2026-01-13T12:00:11+00:00","obs-distractor":"2026-01-13T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-13T12:00:10+00:00","obs-2":"2026-01-13T12:00:27+00:00","obs-distractor":"2026-01-13T12:00:12+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.934,"edge-ai-1":0.652},"confidence":{"obs-1":0.90832,"obs-2":0.90832,"obs-distractor":0.72},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88137088,"event_time":"2026-01-13T12:00:11+00:00","arrival_time":"2026-01-13T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88137088,"normal":0.11862912000000003},"reference_distribution":{"anomalous":0.88137088,"normal":0.11862912000000003}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88137088,"event_time":"2026-01-13T12:00:10+00:00","arrival_time":"2026-01-13T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.88137088,"normal":0.11862912000000003}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-13T12:00:10+00:00","arrival_time":"2026-01-13T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.88137088,"event_time":"2026-01-13T12:00:12+00:00","arrival_time":"2026-01-13T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88137088,"normal":0.11862912000000003},"reference_distribution":{"anomalous":0.88137088,"normal":0.11862912000000003}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-13T12:00:12+00:00","arrival_time":"2026-01-13T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88137088,"event_time":"2026-01-13T12:00:11+00:00","arrival_time":"2026-01-13T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88137088,"normal":0.11862912000000003},"reference_distribution":{"anomalous":0.88137088,"normal":0.11862912000000003}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-13T12:00:11+00:00","arrival_time":"2026-01-13T12:00:27+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":24,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-012","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"139a535652c1778bbe0de46b83d229af2fd0772b597684a9a92c62009934d539"}}
{"id":"evaluation-v1-relation_association-20260725-025","name":"Evaluation v1.0 trajectory: relation_association case 025","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-012","label":"Distractor 012","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90832,"modality":"semantic_status","timestamp":"2026-01-13T12:00:10Z","metadata":{"arrival_time":"2026-01-13T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90832,"modality":"semantic_status","timestamp":"2026-01-13T12:00:11Z","metadata":{"arrival_time":"2026-01-13T12:00:27+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-012","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.72,"modality":"semantic_status","timestamp":"2026-01-13T12:00:12Z","metadata":{"arrival_time":"2026-01-13T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-13T12:00:10+00:00","obs-2":"2026-01-13T12:00:11+00:00","obs-distractor":"2026-01-13T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-13T12:00:10+00:00","obs-2":"2026-01-13T12:00:27+00:00","obs-distractor":"2026-01-13T12:00:12+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.934,"edge-ai-1":0.652},"confidence":{"obs-1":0.90832,"obs-2":0.90832,"obs-distractor":0.72},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88137088,"event_time":"2026-01-13T12:00:11+00:00","arrival_time":"2026-01-13T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11862912000000003,"normal":0.88137088}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-13T12:00:10+00:00","arrival_time":"2026-01-13T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-13T12:00:10+00:00","arrival_time":"2026-01-13T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-13T12:00:12+00:00","arrival_time":"2026-01-13T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-13T12:00:12+00:00","arrival_time":"2026-01-13T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88137088,"event_time":"2026-01-13T12:00:11+00:00","arrival_time":"2026-01-13T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11862912000000003,"normal":0.88137088}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-13T12:00:11+00:00","arrival_time":"2026-01-13T12:00:27+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":25,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-012","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"9ab1b37e24a0d224d8355faa928a79572f70ddf6d3e71c89714060b46a1dd34e"}}
{"id":"evaluation-v1-relation_association-20260725-026","name":"Evaluation v1.0 trajectory: relation_association case 026","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-013","label":"Distractor 013","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90818,"modality":"semantic_status","timestamp":"2026-01-14T12:00:10Z","metadata":{"arrival_time":"2026-01-14T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-013","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.73,"modality":"semantic_status","timestamp":"2026-01-14T12:00:13Z","metadata":{"arrival_time":"2026-01-14T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90818,"modality":"semantic_status","timestamp":"2026-01-14T12:00:11Z","metadata":{"arrival_time":"2026-01-14T12:00:28+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-14T12:00:10+00:00","obs-distractor":"2026-01-14T12:00:13+00:00","obs-2":"2026-01-14T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-14T12:00:10+00:00","obs-distractor":"2026-01-14T12:00:13+00:00","obs-2":"2026-01-14T12:00:28+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.942,"edge-ai-1":0.52},"confidence":{"obs-1":0.90818,"obs-distractor":0.73,"obs-2":0.90818},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88450556,"event_time":"2026-01-14T12:00:11+00:00","arrival_time":"2026-01-14T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88450556,"normal":0.11549443999999998},"reference_distribution":{"anomalous":0.88450556,"normal":0.11549443999999998}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88450556,"event_time":"2026-01-14T12:00:10+00:00","arrival_time":"2026-01-14T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.88450556,"normal":0.11549443999999998}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-14T12:00:10+00:00","arrival_time":"2026-01-14T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.88450556,"event_time":"2026-01-14T12:00:13+00:00","arrival_time":"2026-01-14T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88450556,"normal":0.11549443999999998},"reference_distribution":{"anomalous":0.88450556,"normal":0.11549443999999998}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-14T12:00:13+00:00","arrival_time":"2026-01-14T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88450556,"event_time":"2026-01-14T12:00:11+00:00","arrival_time":"2026-01-14T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88450556,"normal":0.11549443999999998},"reference_distribution":{"anomalous":0.88450556,"normal":0.11549443999999998}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-14T12:00:11+00:00","arrival_time":"2026-01-14T12:00:28+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":26,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-013","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"278c0dc2f7d9a2d1a351be2ba050ee3ae1ddead2eb1f197e47fed9415505e10e"}}
{"id":"evaluation-v1-relation_association-20260725-027","name":"Evaluation v1.0 trajectory: relation_association case 027","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-013","label":"Distractor 013","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90818,"modality":"semantic_status","timestamp":"2026-01-14T12:00:10Z","metadata":{"arrival_time":"2026-01-14T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-013","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.73,"modality":"semantic_status","timestamp":"2026-01-14T12:00:13Z","metadata":{"arrival_time":"2026-01-14T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90818,"modality":"semantic_status","timestamp":"2026-01-14T12:00:11Z","metadata":{"arrival_time":"2026-01-14T12:00:28+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-14T12:00:10+00:00","obs-distractor":"2026-01-14T12:00:13+00:00","obs-2":"2026-01-14T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-14T12:00:10+00:00","obs-distractor":"2026-01-14T12:00:13+00:00","obs-2":"2026-01-14T12:00:28+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.942,"edge-ai-1":0.52},"confidence":{"obs-1":0.90818,"obs-distractor":0.73,"obs-2":0.90818},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88450556,"event_time":"2026-01-14T12:00:11+00:00","arrival_time":"2026-01-14T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11549443999999998,"normal":0.88450556}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-14T12:00:10+00:00","arrival_time":"2026-01-14T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-14T12:00:10+00:00","arrival_time":"2026-01-14T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-14T12:00:13+00:00","arrival_time":"2026-01-14T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-14T12:00:13+00:00","arrival_time":"2026-01-14T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88450556,"event_time":"2026-01-14T12:00:11+00:00","arrival_time":"2026-01-14T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11549443999999998,"normal":0.88450556}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-14T12:00:11+00:00","arrival_time":"2026-01-14T12:00:28+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":27,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-013","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"e1f7b4e509d6263873a7ab3a0d7d33403a4cb0d392cf66545d135804760b04bd"}}
{"id":"evaluation-v1-relation_association-20260725-028","name":"Evaluation v1.0 trajectory: relation_association case 028","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-014","label":"Distractor 014","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90804,"modality":"semantic_status","timestamp":"2026-01-15T12:00:10Z","metadata":{"arrival_time":"2026-01-15T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90804,"modality":"semantic_status","timestamp":"2026-01-15T12:00:11Z","metadata":{"arrival_time":"2026-01-15T12:00:29+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-014","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.74,"modality":"semantic_status","timestamp":"2026-01-15T12:00:14Z","metadata":{"arrival_time":"2026-01-15T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-15T12:00:10+00:00","obs-2":"2026-01-15T12:00:11+00:00","obs-distractor":"2026-01-15T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-15T12:00:10+00:00","obs-2":"2026-01-15T12:00:29+00:00","obs-distractor":"2026-01-15T12:00:14+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.95,"edge-ai-1":0.531},"confidence":{"obs-1":0.90804,"obs-2":0.90804,"obs-distractor":0.74},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8876379999999999,"event_time":"2026-01-15T12:00:11+00:00","arrival_time":"2026-01-15T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8876379999999999,"normal":0.11236200000000007},"reference_distribution":{"anomalous":0.8876379999999999,"normal":0.11236200000000007}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8876379999999999,"event_time":"2026-01-15T12:00:10+00:00","arrival_time":"2026-01-15T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8876379999999999,"normal":0.11236200000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-15T12:00:10+00:00","arrival_time":"2026-01-15T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8876379999999999,"event_time":"2026-01-15T12:00:14+00:00","arrival_time":"2026-01-15T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8876379999999999,"normal":0.11236200000000007},"reference_distribution":{"anomalous":0.8876379999999999,"normal":0.11236200000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-15T12:00:14+00:00","arrival_time":"2026-01-15T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8876379999999999,"event_time":"2026-01-15T12:00:11+00:00","arrival_time":"2026-01-15T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8876379999999999,"normal":0.11236200000000007},"reference_distribution":{"anomalous":0.8876379999999999,"normal":0.11236200000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-15T12:00:11+00:00","arrival_time":"2026-01-15T12:00:29+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":28,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-014","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"8265999ee1246725be9a4ba3cbfb5fc5e59f83f001fd892ccd520a06a2e2e23b"}}
{"id":"evaluation-v1-relation_association-20260725-029","name":"Evaluation v1.0 trajectory: relation_association case 029","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-014","label":"Distractor 014","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90804,"modality":"semantic_status","timestamp":"2026-01-15T12:00:10Z","metadata":{"arrival_time":"2026-01-15T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90804,"modality":"semantic_status","timestamp":"2026-01-15T12:00:11Z","metadata":{"arrival_time":"2026-01-15T12:00:29+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-014","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.74,"modality":"semantic_status","timestamp":"2026-01-15T12:00:14Z","metadata":{"arrival_time":"2026-01-15T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-15T12:00:10+00:00","obs-2":"2026-01-15T12:00:11+00:00","obs-distractor":"2026-01-15T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-15T12:00:10+00:00","obs-2":"2026-01-15T12:00:29+00:00","obs-distractor":"2026-01-15T12:00:14+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.95,"edge-ai-1":0.531},"confidence":{"obs-1":0.90804,"obs-2":0.90804,"obs-distractor":0.74},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8876379999999999,"event_time":"2026-01-15T12:00:11+00:00","arrival_time":"2026-01-15T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11236200000000007,"normal":0.8876379999999999}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-15T12:00:10+00:00","arrival_time":"2026-01-15T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-15T12:00:10+00:00","arrival_time":"2026-01-15T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-15T12:00:14+00:00","arrival_time":"2026-01-15T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-15T12:00:14+00:00","arrival_time":"2026-01-15T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8876379999999999,"event_time":"2026-01-15T12:00:11+00:00","arrival_time":"2026-01-15T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11236200000000007,"normal":0.8876379999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-15T12:00:11+00:00","arrival_time":"2026-01-15T12:00:29+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":29,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-014","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"ee339b6486d905d3045acc17a94e63cda3a86d45877b6e2e3039baa1feff9c6d"}}
{"id":"evaluation-v1-relation_association-20260725-030","name":"Evaluation v1.0 trajectory: relation_association case 030","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-015","label":"Distractor 015","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.9079,"modality":"semantic_status","timestamp":"2026-01-16T12:00:10Z","metadata":{"arrival_time":"2026-01-16T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-015","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.75,"modality":"semantic_status","timestamp":"2026-01-16T12:00:12Z","metadata":{"arrival_time":"2026-01-16T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.9079,"modality":"semantic_status","timestamp":"2026-01-16T12:00:11Z","metadata":{"arrival_time":"2026-01-16T12:00:30+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-16T12:00:10+00:00","obs-distractor":"2026-01-16T12:00:12+00:00","obs-2":"2026-01-16T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-16T12:00:10+00:00","obs-distractor":"2026-01-16T12:00:12+00:00","obs-2":"2026-01-16T12:00:30+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.958,"edge-ai-1":0.542},"confidence":{"obs-1":0.9079,"obs-distractor":0.75,"obs-2":0.9079},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8907682,"event_time":"2026-01-16T12:00:11+00:00","arrival_time":"2026-01-16T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8907682,"normal":0.10923179999999999},"reference_distribution":{"anomalous":0.8907682,"normal":0.10923179999999999}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8907682,"event_time":"2026-01-16T12:00:10+00:00","arrival_time":"2026-01-16T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8907682,"normal":0.10923179999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-16T12:00:10+00:00","arrival_time":"2026-01-16T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8907682,"event_time":"2026-01-16T12:00:12+00:00","arrival_time":"2026-01-16T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8907682,"normal":0.10923179999999999},"reference_distribution":{"anomalous":0.8907682,"normal":0.10923179999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-16T12:00:12+00:00","arrival_time":"2026-01-16T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8907682,"event_time":"2026-01-16T12:00:11+00:00","arrival_time":"2026-01-16T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8907682,"normal":0.10923179999999999},"reference_distribution":{"anomalous":0.8907682,"normal":0.10923179999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-16T12:00:11+00:00","arrival_time":"2026-01-16T12:00:30+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":30,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-015","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"7ba0ea756b3ab4d3bb48bfa650ea64dbd4e8363bd5434828766d38c7bf563404"}}
{"id":"evaluation-v1-relation_association-20260725-031","name":"Evaluation v1.0 trajectory: relation_association case 031","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-015","label":"Distractor 015","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.9079,"modality":"semantic_status","timestamp":"2026-01-16T12:00:10Z","metadata":{"arrival_time":"2026-01-16T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-015","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.75,"modality":"semantic_status","timestamp":"2026-01-16T12:00:12Z","metadata":{"arrival_time":"2026-01-16T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.9079,"modality":"semantic_status","timestamp":"2026-01-16T12:00:11Z","metadata":{"arrival_time":"2026-01-16T12:00:30+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-16T12:00:10+00:00","obs-distractor":"2026-01-16T12:00:12+00:00","obs-2":"2026-01-16T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-16T12:00:10+00:00","obs-distractor":"2026-01-16T12:00:12+00:00","obs-2":"2026-01-16T12:00:30+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.958,"edge-ai-1":0.542},"confidence":{"obs-1":0.9079,"obs-distractor":0.75,"obs-2":0.9079},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8907682,"event_time":"2026-01-16T12:00:11+00:00","arrival_time":"2026-01-16T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10923179999999999,"normal":0.8907682}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-16T12:00:10+00:00","arrival_time":"2026-01-16T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-16T12:00:10+00:00","arrival_time":"2026-01-16T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-16T12:00:12+00:00","arrival_time":"2026-01-16T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-16T12:00:12+00:00","arrival_time":"2026-01-16T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8907682,"event_time":"2026-01-16T12:00:11+00:00","arrival_time":"2026-01-16T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10923179999999999,"normal":0.8907682}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-16T12:00:11+00:00","arrival_time":"2026-01-16T12:00:30+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":31,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-015","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"7eb34c03bae653c7c28d685148d7663f9c68d64d682d42d18439f2f2b15824da"}}
{"id":"evaluation-v1-relation_association-20260725-032","name":"Evaluation v1.0 trajectory: relation_association case 032","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-016","label":"Distractor 016","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90776,"modality":"semantic_status","timestamp":"2026-01-17T12:00:10Z","metadata":{"arrival_time":"2026-01-17T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90776,"modality":"semantic_status","timestamp":"2026-01-17T12:00:11Z","metadata":{"arrival_time":"2026-01-17T12:00:31+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-016","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.76,"modality":"semantic_status","timestamp":"2026-01-17T12:00:13Z","metadata":{"arrival_time":"2026-01-17T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-17T12:00:10+00:00","obs-2":"2026-01-17T12:00:11+00:00","obs-distractor":"2026-01-17T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-17T12:00:10+00:00","obs-2":"2026-01-17T12:00:31+00:00","obs-distractor":"2026-01-17T12:00:13+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.966,"edge-ai-1":0.553},"confidence":{"obs-1":0.90776,"obs-2":0.90776,"obs-distractor":0.76},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8938961599999999,"event_time":"2026-01-17T12:00:11+00:00","arrival_time":"2026-01-17T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8938961599999999,"normal":0.10610384000000006},"reference_distribution":{"anomalous":0.8938961599999999,"normal":0.10610384000000006}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8938961599999999,"event_time":"2026-01-17T12:00:10+00:00","arrival_time":"2026-01-17T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8938961599999999,"normal":0.10610384000000006}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-17T12:00:10+00:00","arrival_time":"2026-01-17T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8938961599999999,"event_time":"2026-01-17T12:00:13+00:00","arrival_time":"2026-01-17T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8938961599999999,"normal":0.10610384000000006},"reference_distribution":{"anomalous":0.8938961599999999,"normal":0.10610384000000006}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-17T12:00:13+00:00","arrival_time":"2026-01-17T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8938961599999999,"event_time":"2026-01-17T12:00:11+00:00","arrival_time":"2026-01-17T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8938961599999999,"normal":0.10610384000000006},"reference_distribution":{"anomalous":0.8938961599999999,"normal":0.10610384000000006}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-17T12:00:11+00:00","arrival_time":"2026-01-17T12:00:31+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":32,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-016","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"d69c118bd9f4a8adb0ef9e76bc611647c65a1b28291fc9fe749cb80fdef3fb17"}}
{"id":"evaluation-v1-relation_association-20260725-033","name":"Evaluation v1.0 trajectory: relation_association case 033","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-016","label":"Distractor 016","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90776,"modality":"semantic_status","timestamp":"2026-01-17T12:00:10Z","metadata":{"arrival_time":"2026-01-17T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90776,"modality":"semantic_status","timestamp":"2026-01-17T12:00:11Z","metadata":{"arrival_time":"2026-01-17T12:00:31+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-016","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.76,"modality":"semantic_status","timestamp":"2026-01-17T12:00:13Z","metadata":{"arrival_time":"2026-01-17T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-17T12:00:10+00:00","obs-2":"2026-01-17T12:00:11+00:00","obs-distractor":"2026-01-17T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-17T12:00:10+00:00","obs-2":"2026-01-17T12:00:31+00:00","obs-distractor":"2026-01-17T12:00:13+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.966,"edge-ai-1":0.553},"confidence":{"obs-1":0.90776,"obs-2":0.90776,"obs-distractor":0.76},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8938961599999999,"event_time":"2026-01-17T12:00:11+00:00","arrival_time":"2026-01-17T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10610384000000006,"normal":0.8938961599999999}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-17T12:00:10+00:00","arrival_time":"2026-01-17T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-17T12:00:10+00:00","arrival_time":"2026-01-17T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-17T12:00:13+00:00","arrival_time":"2026-01-17T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-17T12:00:13+00:00","arrival_time":"2026-01-17T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8938961599999999,"event_time":"2026-01-17T12:00:11+00:00","arrival_time":"2026-01-17T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10610384000000006,"normal":0.8938961599999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-17T12:00:11+00:00","arrival_time":"2026-01-17T12:00:31+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":33,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-016","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"a9cc9b407d30eeb458a00cce906f017b4c6c244a5979c07e514ea30004e06ca5"}}
{"id":"evaluation-v1-relation_association-20260725-034","name":"Evaluation v1.0 trajectory: relation_association case 034","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-017","label":"Distractor 017","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90762,"modality":"semantic_status","timestamp":"2026-01-18T12:00:10Z","metadata":{"arrival_time":"2026-01-18T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90762,"modality":"semantic_status","timestamp":"2026-01-18T12:00:11Z","metadata":{"arrival_time":"2026-01-18T12:00:15+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-017","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.77,"modality":"semantic_status","timestamp":"2026-01-18T12:00:14Z","metadata":{"arrival_time":"2026-01-18T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-18T12:00:10+00:00","obs-2":"2026-01-18T12:00:11+00:00","obs-distractor":"2026-01-18T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-18T12:00:10+00:00","obs-2":"2026-01-18T12:00:15+00:00","obs-distractor":"2026-01-18T12:00:14+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.974,"edge-ai-1":0.564},"confidence":{"obs-1":0.90762,"obs-2":0.90762,"obs-distractor":0.77},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.89702188,"event_time":"2026-01-18T12:00:11+00:00","arrival_time":"2026-01-18T12:00:15+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.89702188,"normal":0.10297811999999995},"reference_distribution":{"anomalous":0.89702188,"normal":0.10297811999999995}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.89702188,"event_time":"2026-01-18T12:00:10+00:00","arrival_time":"2026-01-18T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.89702188,"normal":0.10297811999999995}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-18T12:00:10+00:00","arrival_time":"2026-01-18T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.89702188,"event_time":"2026-01-18T12:00:14+00:00","arrival_time":"2026-01-18T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.89702188,"normal":0.10297811999999995},"reference_distribution":{"anomalous":0.89702188,"normal":0.10297811999999995}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-18T12:00:14+00:00","arrival_time":"2026-01-18T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.89702188,"event_time":"2026-01-18T12:00:11+00:00","arrival_time":"2026-01-18T12:00:15+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.89702188,"normal":0.10297811999999995},"reference_distribution":{"anomalous":0.89702188,"normal":0.10297811999999995}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-18T12:00:11+00:00","arrival_time":"2026-01-18T12:00:15+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":34,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-017","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"d123967972d873712edcc142b86262ea9057824d6c159f58c96d68c20be89154"}}
{"id":"evaluation-v1-relation_association-20260725-035","name":"Evaluation v1.0 trajectory: relation_association case 035","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-017","label":"Distractor 017","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90762,"modality":"semantic_status","timestamp":"2026-01-18T12:00:10Z","metadata":{"arrival_time":"2026-01-18T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90762,"modality":"semantic_status","timestamp":"2026-01-18T12:00:11Z","metadata":{"arrival_time":"2026-01-18T12:00:15+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-017","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.77,"modality":"semantic_status","timestamp":"2026-01-18T12:00:14Z","metadata":{"arrival_time":"2026-01-18T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-18T12:00:10+00:00","obs-2":"2026-01-18T12:00:11+00:00","obs-distractor":"2026-01-18T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-18T12:00:10+00:00","obs-2":"2026-01-18T12:00:15+00:00","obs-distractor":"2026-01-18T12:00:14+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.974,"edge-ai-1":0.564},"confidence":{"obs-1":0.90762,"obs-2":0.90762,"obs-distractor":0.77},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.89702188,"event_time":"2026-01-18T12:00:11+00:00","arrival_time":"2026-01-18T12:00:15+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10297811999999995,"normal":0.89702188}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-18T12:00:10+00:00","arrival_time":"2026-01-18T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-18T12:00:10+00:00","arrival_time":"2026-01-18T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-18T12:00:14+00:00","arrival_time":"2026-01-18T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-18T12:00:14+00:00","arrival_time":"2026-01-18T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.89702188,"event_time":"2026-01-18T12:00:11+00:00","arrival_time":"2026-01-18T12:00:15+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.10297811999999995,"normal":0.89702188}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-18T12:00:11+00:00","arrival_time":"2026-01-18T12:00:15+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":35,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-017","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"31e3acac8f18fcd42046c3553d55434d299714b0dfdb4bcd57b97163c2603654"}}
{"id":"evaluation-v1-relation_association-20260725-036","name":"Evaluation v1.0 trajectory: relation_association case 036","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-018","label":"Distractor 018","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90748,"modality":"semantic_status","timestamp":"2026-01-19T12:00:10Z","metadata":{"arrival_time":"2026-01-19T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90748,"modality":"semantic_status","timestamp":"2026-01-19T12:00:11Z","metadata":{"arrival_time":"2026-01-19T12:00:16+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-018","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.78,"modality":"semantic_status","timestamp":"2026-01-19T12:00:12Z","metadata":{"arrival_time":"2026-01-19T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-19T12:00:10+00:00","obs-2":"2026-01-19T12:00:11+00:00","obs-distractor":"2026-01-19T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-19T12:00:10+00:00","obs-2":"2026-01-19T12:00:16+00:00","obs-distractor":"2026-01-19T12:00:12+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.91,"edge-ai-1":0.575},"confidence":{"obs-1":0.90748,"obs-2":0.90748,"obs-distractor":0.78},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8708068,"event_time":"2026-01-19T12:00:11+00:00","arrival_time":"2026-01-19T12:00:16+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8708068,"normal":0.1291932},"reference_distribution":{"anomalous":0.8708068,"normal":0.1291932}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8708068,"event_time":"2026-01-19T12:00:10+00:00","arrival_time":"2026-01-19T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8708068,"normal":0.1291932}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-19T12:00:10+00:00","arrival_time":"2026-01-19T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8708068,"event_time":"2026-01-19T12:00:12+00:00","arrival_time":"2026-01-19T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8708068,"normal":0.1291932},"reference_distribution":{"anomalous":0.8708068,"normal":0.1291932}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-19T12:00:12+00:00","arrival_time":"2026-01-19T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8708068,"event_time":"2026-01-19T12:00:11+00:00","arrival_time":"2026-01-19T12:00:16+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8708068,"normal":0.1291932},"reference_distribution":{"anomalous":0.8708068,"normal":0.1291932}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-19T12:00:11+00:00","arrival_time":"2026-01-19T12:00:16+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":36,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-018","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"48198a0ef1744bb67f620c9d579825f0d56bbd8fb4675e13f125b1af4bff0ba3"}}
{"id":"evaluation-v1-relation_association-20260725-037","name":"Evaluation v1.0 trajectory: relation_association case 037","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-018","label":"Distractor 018","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90748,"modality":"semantic_status","timestamp":"2026-01-19T12:00:10Z","metadata":{"arrival_time":"2026-01-19T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90748,"modality":"semantic_status","timestamp":"2026-01-19T12:00:11Z","metadata":{"arrival_time":"2026-01-19T12:00:16+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-018","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.78,"modality":"semantic_status","timestamp":"2026-01-19T12:00:12Z","metadata":{"arrival_time":"2026-01-19T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-19T12:00:10+00:00","obs-2":"2026-01-19T12:00:11+00:00","obs-distractor":"2026-01-19T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-19T12:00:10+00:00","obs-2":"2026-01-19T12:00:16+00:00","obs-distractor":"2026-01-19T12:00:12+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.91,"edge-ai-1":0.575},"confidence":{"obs-1":0.90748,"obs-2":0.90748,"obs-distractor":0.78},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8708068,"event_time":"2026-01-19T12:00:11+00:00","arrival_time":"2026-01-19T12:00:16+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1291932,"normal":0.8708068}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-19T12:00:10+00:00","arrival_time":"2026-01-19T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-19T12:00:10+00:00","arrival_time":"2026-01-19T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-19T12:00:12+00:00","arrival_time":"2026-01-19T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-19T12:00:12+00:00","arrival_time":"2026-01-19T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8708068,"event_time":"2026-01-19T12:00:11+00:00","arrival_time":"2026-01-19T12:00:16+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1291932,"normal":0.8708068}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-19T12:00:11+00:00","arrival_time":"2026-01-19T12:00:16+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":37,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-018","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"9754dc75fa36c52b67af2cc431ac091fa480facec607adb3d6e92cf7f9c01768"}}
{"id":"evaluation-v1-relation_association-20260725-038","name":"Evaluation v1.0 trajectory: relation_association case 038","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-019","label":"Distractor 019","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90734,"modality":"semantic_status","timestamp":"2026-01-20T12:00:10Z","metadata":{"arrival_time":"2026-01-20T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-019","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.79,"modality":"semantic_status","timestamp":"2026-01-20T12:00:13Z","metadata":{"arrival_time":"2026-01-20T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90734,"modality":"semantic_status","timestamp":"2026-01-20T12:00:11Z","metadata":{"arrival_time":"2026-01-20T12:00:17+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-20T12:00:10+00:00","obs-distractor":"2026-01-20T12:00:13+00:00","obs-2":"2026-01-20T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-20T12:00:10+00:00","obs-distractor":"2026-01-20T12:00:13+00:00","obs-2":"2026-01-20T12:00:17+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.918,"edge-ai-1":0.586},"confidence":{"obs-1":0.90734,"obs-distractor":0.79,"obs-2":0.90734},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87393812,"event_time":"2026-01-20T12:00:11+00:00","arrival_time":"2026-01-20T12:00:17+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.87393812,"normal":0.12606187999999996},"reference_distribution":{"anomalous":0.87393812,"normal":0.12606187999999996}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87393812,"event_time":"2026-01-20T12:00:10+00:00","arrival_time":"2026-01-20T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.87393812,"normal":0.12606187999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-20T12:00:10+00:00","arrival_time":"2026-01-20T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.87393812,"event_time":"2026-01-20T12:00:13+00:00","arrival_time":"2026-01-20T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.87393812,"normal":0.12606187999999996},"reference_distribution":{"anomalous":0.87393812,"normal":0.12606187999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-20T12:00:13+00:00","arrival_time":"2026-01-20T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87393812,"event_time":"2026-01-20T12:00:11+00:00","arrival_time":"2026-01-20T12:00:17+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.87393812,"normal":0.12606187999999996},"reference_distribution":{"anomalous":0.87393812,"normal":0.12606187999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-20T12:00:11+00:00","arrival_time":"2026-01-20T12:00:17+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":38,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-019","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"84ff1d490a3ea95184a61f31e2f919e4c01b10a28f178b4138fd301d425392dd"}}
{"id":"evaluation-v1-relation_association-20260725-039","name":"Evaluation v1.0 trajectory: relation_association case 039","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-019","label":"Distractor 019","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90734,"modality":"semantic_status","timestamp":"2026-01-20T12:00:10Z","metadata":{"arrival_time":"2026-01-20T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-019","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.79,"modality":"semantic_status","timestamp":"2026-01-20T12:00:13Z","metadata":{"arrival_time":"2026-01-20T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90734,"modality":"semantic_status","timestamp":"2026-01-20T12:00:11Z","metadata":{"arrival_time":"2026-01-20T12:00:17+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-20T12:00:10+00:00","obs-distractor":"2026-01-20T12:00:13+00:00","obs-2":"2026-01-20T12:00:11+00:00"},"arrival_times":{"obs-1":"2026-01-20T12:00:10+00:00","obs-distractor":"2026-01-20T12:00:13+00:00","obs-2":"2026-01-20T12:00:17+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.918,"edge-ai-1":0.586},"confidence":{"obs-1":0.90734,"obs-distractor":0.79,"obs-2":0.90734},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87393812,"event_time":"2026-01-20T12:00:11+00:00","arrival_time":"2026-01-20T12:00:17+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.12606187999999996,"normal":0.87393812}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-20T12:00:10+00:00","arrival_time":"2026-01-20T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-20T12:00:10+00:00","arrival_time":"2026-01-20T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-20T12:00:13+00:00","arrival_time":"2026-01-20T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-20T12:00:13+00:00","arrival_time":"2026-01-20T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87393812,"event_time":"2026-01-20T12:00:11+00:00","arrival_time":"2026-01-20T12:00:17+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.12606187999999996,"normal":0.87393812}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-20T12:00:11+00:00","arrival_time":"2026-01-20T12:00:17+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":39,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-019","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"e120b004a0f051eeeb7f36fa7745645b5854081685af9a045a38ee4da3b6ea1a"}}
{"id":"evaluation-v1-relation_association-20260725-040","name":"Evaluation v1.0 trajectory: relation_association case 040","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-020","label":"Distractor 020","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.9072,"modality":"semantic_status","timestamp":"2026-01-21T12:00:10Z","metadata":{"arrival_time":"2026-01-21T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.9072,"modality":"semantic_status","timestamp":"2026-01-21T12:00:11Z","metadata":{"arrival_time":"2026-01-21T12:00:18+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-020","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-01-21T12:00:14Z","metadata":{"arrival_time":"2026-01-21T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-21T12:00:10+00:00","obs-2":"2026-01-21T12:00:11+00:00","obs-distractor":"2026-01-21T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-21T12:00:10+00:00","obs-2":"2026-01-21T12:00:18+00:00","obs-distractor":"2026-01-21T12:00:14+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.926,"edge-ai-1":0.597},"confidence":{"obs-1":0.9072,"obs-2":0.9072,"obs-distractor":0.6},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8770672,"event_time":"2026-01-21T12:00:11+00:00","arrival_time":"2026-01-21T12:00:18+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8770672,"normal":0.12293279999999995},"reference_distribution":{"anomalous":0.8770672,"normal":0.12293279999999995}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8770672,"event_time":"2026-01-21T12:00:10+00:00","arrival_time":"2026-01-21T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8770672,"normal":0.12293279999999995}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-21T12:00:10+00:00","arrival_time":"2026-01-21T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8770672,"event_time":"2026-01-21T12:00:14+00:00","arrival_time":"2026-01-21T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8770672,"normal":0.12293279999999995},"reference_distribution":{"anomalous":0.8770672,"normal":0.12293279999999995}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-21T12:00:14+00:00","arrival_time":"2026-01-21T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8770672,"event_time":"2026-01-21T12:00:11+00:00","arrival_time":"2026-01-21T12:00:18+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8770672,"normal":0.12293279999999995},"reference_distribution":{"anomalous":0.8770672,"normal":0.12293279999999995}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-21T12:00:11+00:00","arrival_time":"2026-01-21T12:00:18+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":40,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-020","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"269da8810367ca122067a5194d0070567fdc2190598a26a26a827ed7ca666bc3"}}
{"id":"evaluation-v1-relation_association-20260725-041","name":"Evaluation v1.0 trajectory: relation_association case 041","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-020","label":"Distractor 020","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.9072,"modality":"semantic_status","timestamp":"2026-01-21T12:00:10Z","metadata":{"arrival_time":"2026-01-21T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.9072,"modality":"semantic_status","timestamp":"2026-01-21T12:00:11Z","metadata":{"arrival_time":"2026-01-21T12:00:18+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-020","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-01-21T12:00:14Z","metadata":{"arrival_time":"2026-01-21T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-21T12:00:10+00:00","obs-2":"2026-01-21T12:00:11+00:00","obs-distractor":"2026-01-21T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-21T12:00:10+00:00","obs-2":"2026-01-21T12:00:18+00:00","obs-distractor":"2026-01-21T12:00:14+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.926,"edge-ai-1":0.597},"confidence":{"obs-1":0.9072,"obs-2":0.9072,"obs-distractor":0.6},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8770672,"event_time":"2026-01-21T12:00:11+00:00","arrival_time":"2026-01-21T12:00:18+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.12293279999999995,"normal":0.8770672}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-21T12:00:10+00:00","arrival_time":"2026-01-21T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-21T12:00:10+00:00","arrival_time":"2026-01-21T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-21T12:00:14+00:00","arrival_time":"2026-01-21T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-21T12:00:14+00:00","arrival_time":"2026-01-21T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8770672,"event_time":"2026-01-21T12:00:11+00:00","arrival_time":"2026-01-21T12:00:18+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.12293279999999995,"normal":0.8770672}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-21T12:00:11+00:00","arrival_time":"2026-01-21T12:00:18+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":41,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-020","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"833780848d07b70c79613650cdb96e8d564b5a00d997702fc0bb30233f66c9c2"}}
{"id":"evaluation-v1-relation_association-20260725-042","name":"Evaluation v1.0 trajectory: relation_association case 042","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-021","label":"Distractor 021","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90706,"modality":"semantic_status","timestamp":"2026-01-22T12:00:10Z","metadata":{"arrival_time":"2026-01-22T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90706,"modality":"semantic_status","timestamp":"2026-01-22T12:00:11Z","metadata":{"arrival_time":"2026-01-22T12:00:19+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-021","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-01-22T12:00:12Z","metadata":{"arrival_time":"2026-01-22T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-22T12:00:10+00:00","obs-2":"2026-01-22T12:00:11+00:00","obs-distractor":"2026-01-22T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-22T12:00:10+00:00","obs-2":"2026-01-22T12:00:19+00:00","obs-distractor":"2026-01-22T12:00:12+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.934,"edge-ai-1":0.608},"confidence":{"obs-1":0.90706,"obs-2":0.90706,"obs-distractor":0.61},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88019404,"event_time":"2026-01-22T12:00:11+00:00","arrival_time":"2026-01-22T12:00:19+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88019404,"normal":0.11980595999999999},"reference_distribution":{"anomalous":0.88019404,"normal":0.11980595999999999}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88019404,"event_time":"2026-01-22T12:00:10+00:00","arrival_time":"2026-01-22T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.88019404,"normal":0.11980595999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-22T12:00:10+00:00","arrival_time":"2026-01-22T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.88019404,"event_time":"2026-01-22T12:00:12+00:00","arrival_time":"2026-01-22T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88019404,"normal":0.11980595999999999},"reference_distribution":{"anomalous":0.88019404,"normal":0.11980595999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-22T12:00:12+00:00","arrival_time":"2026-01-22T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88019404,"event_time":"2026-01-22T12:00:11+00:00","arrival_time":"2026-01-22T12:00:19+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88019404,"normal":0.11980595999999999},"reference_distribution":{"anomalous":0.88019404,"normal":0.11980595999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-22T12:00:11+00:00","arrival_time":"2026-01-22T12:00:19+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":42,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-021","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"ed643867da0c46af93349b097597c5a141ab4d6dc0fefce232e4f25f72119fd2"}}
{"id":"evaluation-v1-relation_association-20260725-043","name":"Evaluation v1.0 trajectory: relation_association case 043","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-021","label":"Distractor 021","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90706,"modality":"semantic_status","timestamp":"2026-01-22T12:00:10Z","metadata":{"arrival_time":"2026-01-22T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90706,"modality":"semantic_status","timestamp":"2026-01-22T12:00:11Z","metadata":{"arrival_time":"2026-01-22T12:00:19+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-021","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-01-22T12:00:12Z","metadata":{"arrival_time":"2026-01-22T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-22T12:00:10+00:00","obs-2":"2026-01-22T12:00:11+00:00","obs-distractor":"2026-01-22T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-22T12:00:10+00:00","obs-2":"2026-01-22T12:00:19+00:00","obs-distractor":"2026-01-22T12:00:12+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.934,"edge-ai-1":0.608},"confidence":{"obs-1":0.90706,"obs-2":0.90706,"obs-distractor":0.61},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88019404,"event_time":"2026-01-22T12:00:11+00:00","arrival_time":"2026-01-22T12:00:19+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11980595999999999,"normal":0.88019404}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-22T12:00:10+00:00","arrival_time":"2026-01-22T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-22T12:00:10+00:00","arrival_time":"2026-01-22T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-22T12:00:12+00:00","arrival_time":"2026-01-22T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-22T12:00:12+00:00","arrival_time":"2026-01-22T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88019404,"event_time":"2026-01-22T12:00:11+00:00","arrival_time":"2026-01-22T12:00:19+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11980595999999999,"normal":0.88019404}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-22T12:00:11+00:00","arrival_time":"2026-01-22T12:00:19+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":43,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-021","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"940d4a47e1ce411caa7dc692a62ebc98bd5ed0898b36a3963a7db752c3bac68a"}}
{"id":"evaluation-v1-relation_association-20260725-044","name":"Evaluation v1.0 trajectory: relation_association case 044","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-022","label":"Distractor 022","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90692,"modality":"semantic_status","timestamp":"2026-01-23T12:00:10Z","metadata":{"arrival_time":"2026-01-23T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90692,"modality":"semantic_status","timestamp":"2026-01-23T12:00:11Z","metadata":{"arrival_time":"2026-01-23T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-022","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-01-23T12:00:13Z","metadata":{"arrival_time":"2026-01-23T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-23T12:00:10+00:00","obs-2":"2026-01-23T12:00:11+00:00","obs-distractor":"2026-01-23T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-23T12:00:10+00:00","obs-2":"2026-01-23T12:00:20+00:00","obs-distractor":"2026-01-23T12:00:13+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.942,"edge-ai-1":0.619},"confidence":{"obs-1":0.90692,"obs-2":0.90692,"obs-distractor":0.62},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8833186399999999,"event_time":"2026-01-23T12:00:11+00:00","arrival_time":"2026-01-23T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8833186399999999,"normal":0.11668136000000007},"reference_distribution":{"anomalous":0.8833186399999999,"normal":0.11668136000000007}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8833186399999999,"event_time":"2026-01-23T12:00:10+00:00","arrival_time":"2026-01-23T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8833186399999999,"normal":0.11668136000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-23T12:00:10+00:00","arrival_time":"2026-01-23T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8833186399999999,"event_time":"2026-01-23T12:00:13+00:00","arrival_time":"2026-01-23T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8833186399999999,"normal":0.11668136000000007},"reference_distribution":{"anomalous":0.8833186399999999,"normal":0.11668136000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-23T12:00:13+00:00","arrival_time":"2026-01-23T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8833186399999999,"event_time":"2026-01-23T12:00:11+00:00","arrival_time":"2026-01-23T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8833186399999999,"normal":0.11668136000000007},"reference_distribution":{"anomalous":0.8833186399999999,"normal":0.11668136000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-23T12:00:11+00:00","arrival_time":"2026-01-23T12:00:20+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":44,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-022","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"5d7150b824d520599bb1fc7cc1249d93e4e0e568eb75b7e1a40368491e3a5e23"}}
{"id":"evaluation-v1-relation_association-20260725-045","name":"Evaluation v1.0 trajectory: relation_association case 045","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-022","label":"Distractor 022","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90692,"modality":"semantic_status","timestamp":"2026-01-23T12:00:10Z","metadata":{"arrival_time":"2026-01-23T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90692,"modality":"semantic_status","timestamp":"2026-01-23T12:00:11Z","metadata":{"arrival_time":"2026-01-23T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-022","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-01-23T12:00:13Z","metadata":{"arrival_time":"2026-01-23T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-23T12:00:10+00:00","obs-2":"2026-01-23T12:00:11+00:00","obs-distractor":"2026-01-23T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-23T12:00:10+00:00","obs-2":"2026-01-23T12:00:20+00:00","obs-distractor":"2026-01-23T12:00:13+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.942,"edge-ai-1":0.619},"confidence":{"obs-1":0.90692,"obs-2":0.90692,"obs-distractor":0.62},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8833186399999999,"event_time":"2026-01-23T12:00:11+00:00","arrival_time":"2026-01-23T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11668136000000007,"normal":0.8833186399999999}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-23T12:00:10+00:00","arrival_time":"2026-01-23T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-23T12:00:10+00:00","arrival_time":"2026-01-23T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-23T12:00:13+00:00","arrival_time":"2026-01-23T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-23T12:00:13+00:00","arrival_time":"2026-01-23T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8833186399999999,"event_time":"2026-01-23T12:00:11+00:00","arrival_time":"2026-01-23T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11668136000000007,"normal":0.8833186399999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-23T12:00:11+00:00","arrival_time":"2026-01-23T12:00:20+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":45,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-022","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"94fc9a8bb195d9d1f3a40798756a8c1d57ac70d74311fc4cda08e05c66073c44"}}
{"id":"evaluation-v1-relation_association-20260725-046","name":"Evaluation v1.0 trajectory: relation_association case 046","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-023","label":"Distractor 023","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90678,"modality":"semantic_status","timestamp":"2026-01-24T12:00:10Z","metadata":{"arrival_time":"2026-01-24T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90678,"modality":"semantic_status","timestamp":"2026-01-24T12:00:11Z","metadata":{"arrival_time":"2026-01-24T12:00:21+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-023","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-01-24T12:00:14Z","metadata":{"arrival_time":"2026-01-24T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-24T12:00:10+00:00","obs-2":"2026-01-24T12:00:11+00:00","obs-distractor":"2026-01-24T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-24T12:00:10+00:00","obs-2":"2026-01-24T12:00:21+00:00","obs-distractor":"2026-01-24T12:00:14+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.95,"edge-ai-1":0.63},"confidence":{"obs-1":0.90678,"obs-2":0.90678,"obs-distractor":0.63},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.886441,"event_time":"2026-01-24T12:00:11+00:00","arrival_time":"2026-01-24T12:00:21+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.886441,"normal":0.11355899999999997},"reference_distribution":{"anomalous":0.886441,"normal":0.11355899999999997}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.886441,"event_time":"2026-01-24T12:00:10+00:00","arrival_time":"2026-01-24T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.886441,"normal":0.11355899999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-24T12:00:10+00:00","arrival_time":"2026-01-24T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.886441,"event_time":"2026-01-24T12:00:14+00:00","arrival_time":"2026-01-24T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.886441,"normal":0.11355899999999997},"reference_distribution":{"anomalous":0.886441,"normal":0.11355899999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-24T12:00:14+00:00","arrival_time":"2026-01-24T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.886441,"event_time":"2026-01-24T12:00:11+00:00","arrival_time":"2026-01-24T12:00:21+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.886441,"normal":0.11355899999999997},"reference_distribution":{"anomalous":0.886441,"normal":0.11355899999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-24T12:00:11+00:00","arrival_time":"2026-01-24T12:00:21+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":46,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-023","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"f8ec86842826e53f8f2d31674454737fe0f479eaf7c5936968333f0cb0df9f70"}}
{"id":"evaluation-v1-relation_association-20260725-047","name":"Evaluation v1.0 trajectory: relation_association case 047","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-023","label":"Distractor 023","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90678,"modality":"semantic_status","timestamp":"2026-01-24T12:00:10Z","metadata":{"arrival_time":"2026-01-24T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90678,"modality":"semantic_status","timestamp":"2026-01-24T12:00:11Z","metadata":{"arrival_time":"2026-01-24T12:00:21+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-023","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-01-24T12:00:14Z","metadata":{"arrival_time":"2026-01-24T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-24T12:00:10+00:00","obs-2":"2026-01-24T12:00:11+00:00","obs-distractor":"2026-01-24T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-24T12:00:10+00:00","obs-2":"2026-01-24T12:00:21+00:00","obs-distractor":"2026-01-24T12:00:14+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.95,"edge-ai-1":0.63},"confidence":{"obs-1":0.90678,"obs-2":0.90678,"obs-distractor":0.63},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.886441,"event_time":"2026-01-24T12:00:11+00:00","arrival_time":"2026-01-24T12:00:21+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11355899999999997,"normal":0.886441}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-24T12:00:10+00:00","arrival_time":"2026-01-24T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-24T12:00:10+00:00","arrival_time":"2026-01-24T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-24T12:00:14+00:00","arrival_time":"2026-01-24T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-24T12:00:14+00:00","arrival_time":"2026-01-24T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.886441,"event_time":"2026-01-24T12:00:11+00:00","arrival_time":"2026-01-24T12:00:21+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11355899999999997,"normal":0.886441}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-24T12:00:11+00:00","arrival_time":"2026-01-24T12:00:21+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":47,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-023","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"2b25da33bfaa8410b99aaefd0546ec7ca78a442963616520d22ad117da8abe60"}}
{"id":"evaluation-v1-relation_association-20260725-048","name":"Evaluation v1.0 trajectory: relation_association case 048","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-024","label":"Distractor 024","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90664,"modality":"semantic_status","timestamp":"2026-01-25T12:00:10Z","metadata":{"arrival_time":"2026-01-25T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90664,"modality":"semantic_status","timestamp":"2026-01-25T12:00:11Z","metadata":{"arrival_time":"2026-01-25T12:00:22+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-024","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-01-25T12:00:12Z","metadata":{"arrival_time":"2026-01-25T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-25T12:00:10+00:00","obs-2":"2026-01-25T12:00:11+00:00","obs-distractor":"2026-01-25T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-25T12:00:10+00:00","obs-2":"2026-01-25T12:00:22+00:00","obs-distractor":"2026-01-25T12:00:12+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.958,"edge-ai-1":0.641},"confidence":{"obs-1":0.90664,"obs-2":0.90664,"obs-distractor":0.64},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88956112,"event_time":"2026-01-25T12:00:11+00:00","arrival_time":"2026-01-25T12:00:22+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88956112,"normal":0.11043888000000002},"reference_distribution":{"anomalous":0.88956112,"normal":0.11043888000000002}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88956112,"event_time":"2026-01-25T12:00:10+00:00","arrival_time":"2026-01-25T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.88956112,"normal":0.11043888000000002}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-25T12:00:10+00:00","arrival_time":"2026-01-25T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.88956112,"event_time":"2026-01-25T12:00:12+00:00","arrival_time":"2026-01-25T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88956112,"normal":0.11043888000000002},"reference_distribution":{"anomalous":0.88956112,"normal":0.11043888000000002}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-25T12:00:12+00:00","arrival_time":"2026-01-25T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88956112,"event_time":"2026-01-25T12:00:11+00:00","arrival_time":"2026-01-25T12:00:22+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.88956112,"normal":0.11043888000000002},"reference_distribution":{"anomalous":0.88956112,"normal":0.11043888000000002}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-a","measures","gauge-1"]],"required_relation_paths":[[["sensor-a","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-25T12:00:11+00:00","arrival_time":"2026-01-25T12:00:22+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":48,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-024","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"1f982154d613996b74a176b5037237237d4de511b09402e0b71f0ac9b8f5ebb2"}}
{"id":"evaluation-v1-relation_association-20260725-049","name":"Evaluation v1.0 trajectory: relation_association case 049","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-024","label":"Distractor 024","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"sensor-a","predicate":"reading","object_id":null,"value":"anomalous","confidence":0.90664,"modality":"semantic_status","timestamp":"2026-01-25T12:00:10Z","metadata":{"arrival_time":"2026-01-25T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"sensor-b","predicate":"reading","object_id":null,"value":"normal","confidence":0.90664,"modality":"semantic_status","timestamp":"2026-01-25T12:00:11Z","metadata":{"arrival_time":"2026-01-25T12:00:22+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-024","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-01-25T12:00:12Z","metadata":{"arrival_time":"2026-01-25T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"sensor-a","target_id":"gauge-2","predicate":"measures","confidence":1.0,"evidence_ids":[]},{"source_id":"sensor-b","target_id":"gauge-1","predicate":"measures","confidence":1.0,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-25T12:00:10+00:00","obs-2":"2026-01-25T12:00:11+00:00","obs-distractor":"2026-01-25T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-25T12:00:10+00:00","obs-2":"2026-01-25T12:00:22+00:00","obs-distractor":"2026-01-25T12:00:12+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.958,"edge-ai-1":0.641},"confidence":{"obs-1":0.90664,"obs-2":0.90664,"obs-distractor":0.64},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88956112,"event_time":"2026-01-25T12:00:11+00:00","arrival_time":"2026-01-25T12:00:22+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11043888000000002,"normal":0.88956112}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.5,"event_time":"2026-01-25T12:00:10+00:00","arrival_time":"2026-01-25T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-25T12:00:10+00:00","arrival_time":"2026-01-25T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.5,"event_time":"2026-01-25T12:00:12+00:00","arrival_time":"2026-01-25T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"request_observation","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":[],"acceptable_supporting_evidence":[],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-25T12:00:12+00:00","arrival_time":"2026-01-25T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","relation_association","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.88956112,"event_time":"2026-01-25T12:00:11+00:00","arrival_time":"2026-01-25T12:00:22+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.11043888000000002,"normal":0.88956112}}],"contradictions":[{"contradiction_id":"evaluation-v1-relation_association-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-2"],"acceptable_supporting_evidence":["obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[["sensor-b","measures","gauge-1"]],"required_relation_paths":[[["sensor-b","measures","gauge-1"]]],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-25T12:00:11+00:00","arrival_time":"2026-01-25T12:00:22+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"relation_association","case_index":49,"suite_seed":20260725,"counterfactual_pair_id":"relation-pair-024","confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"f7eee5c9eed7d859088c374ff6c19c18029a2fad2ac3caf86b3b9eba9b81a9e6"}}
{"id":"evaluation-v1-contradiction_onset-20260725-000","name":"Evaluation v1.0 trajectory: contradiction_onset case 000","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-000","label":"Distractor 000","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.81,"modality":"semantic_status","timestamp":"2026-01-01T12:00:10Z","metadata":{"arrival_time":"2026-01-01T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.82,"modality":"semantic_status","timestamp":"2026-01-01T12:00:20Z","metadata":{"arrival_time":"2026-01-01T12:00:24+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-000","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-01-01T12:00:12Z","metadata":{"arrival_time":"2026-01-01T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-01T12:00:10+00:00","obs-2":"2026-01-01T12:00:20+00:00","obs-distractor":"2026-01-01T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-01T12:00:10+00:00","obs-2":"2026-01-01T12:00:24+00:00","obs-distractor":"2026-01-01T12:00:12+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.91,"edge-ai-1":0.52},"confidence":{"obs-1":0.81,"obs-2":0.82,"obs-distractor":0.6},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-000-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5452424841236468,"event_time":"2026-01-01T12:00:20+00:00","arrival_time":"2026-01-01T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.21789999999999998,"normal":0.7821},"reference_distribution":{"anomalous":0.4547575158763532,"normal":0.5452424841236468}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7821,"event_time":"2026-01-01T12:00:10+00:00","arrival_time":"2026-01-01T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.21789999999999998,"normal":0.7821}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-01T12:00:10+00:00","arrival_time":"2026-01-01T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7821,"event_time":"2026-01-01T12:00:12+00:00","arrival_time":"2026-01-01T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.21789999999999998,"normal":0.7821},"reference_distribution":{"anomalous":0.21789999999999998,"normal":0.7821}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-01T12:00:12+00:00","arrival_time":"2026-01-01T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5452424841236468,"event_time":"2026-01-01T12:00:20+00:00","arrival_time":"2026-01-01T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.21789999999999998,"normal":0.7821},"reference_distribution":{"anomalous":0.4547575158763532,"normal":0.5452424841236468}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-000-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-01T12:00:20+00:00","arrival_time":"2026-01-01T12:00:24+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":0,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"83d9bb6d2ad412f07b00b992270cfbb6fe403a835b8de936a57cb768c0454b14"}}
{"id":"evaluation-v1-contradiction_onset-20260725-001","name":"Evaluation v1.0 trajectory: contradiction_onset case 001","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-001","label":"Distractor 001","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.810233,"modality":"semantic_status","timestamp":"2026-01-02T12:00:10Z","metadata":{"arrival_time":"2026-01-02T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.820175,"modality":"semantic_status","timestamp":"2026-01-02T12:00:20Z","metadata":{"arrival_time":"2026-01-02T12:00:25+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-001","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-01-02T12:00:13Z","metadata":{"arrival_time":"2026-01-02T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-02T12:00:10+00:00","obs-2":"2026-01-02T12:00:20+00:00","obs-distractor":"2026-01-02T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-02T12:00:10+00:00","obs-2":"2026-01-02T12:00:25+00:00","obs-distractor":"2026-01-02T12:00:13+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.918,"edge-ai-1":0.531},"confidence":{"obs-1":0.810233,"obs-2":0.820175,"obs-distractor":0.61},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-001-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5690047464523134,"event_time":"2026-01-02T12:00:20+00:00","arrival_time":"2026-01-02T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.255226163,"normal":0.744773837},"reference_distribution":{"anomalous":0.5690047464523134,"normal":0.4309952535476867}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.744773837,"event_time":"2026-01-02T12:00:10+00:00","arrival_time":"2026-01-02T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.255226163,"normal":0.744773837}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-02T12:00:10+00:00","arrival_time":"2026-01-02T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.744773837,"event_time":"2026-01-02T12:00:13+00:00","arrival_time":"2026-01-02T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.255226163,"normal":0.744773837},"reference_distribution":{"anomalous":0.255226163,"normal":0.744773837}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-02T12:00:13+00:00","arrival_time":"2026-01-02T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5690047464523134,"event_time":"2026-01-02T12:00:20+00:00","arrival_time":"2026-01-02T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.255226163,"normal":0.744773837},"reference_distribution":{"anomalous":0.5690047464523134,"normal":0.4309952535476867}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-001-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-02T12:00:20+00:00","arrival_time":"2026-01-02T12:00:25+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":1,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"222745e813d3b13555bd743163d9720da52b2d9bb7a4451283d39063376952d9"}}
{"id":"evaluation-v1-contradiction_onset-20260725-002","name":"Evaluation v1.0 trajectory: contradiction_onset case 002","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-002","label":"Distractor 002","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.810467,"modality":"semantic_status","timestamp":"2026-01-03T12:00:10Z","metadata":{"arrival_time":"2026-01-03T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-002","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-01-03T12:00:14Z","metadata":{"arrival_time":"2026-01-03T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.82035,"modality":"semantic_status","timestamp":"2026-01-03T12:00:20Z","metadata":{"arrival_time":"2026-01-03T12:00:26+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-03T12:00:10+00:00","obs-distractor":"2026-01-03T12:00:14+00:00","obs-2":"2026-01-03T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-03T12:00:10+00:00","obs-distractor":"2026-01-03T12:00:14+00:00","obs-2":"2026-01-03T12:00:26+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.926,"edge-ai-1":0.542},"confidence":{"obs-1":0.810467,"obs-distractor":0.62,"obs-2":0.82035},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-002-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5451163248893276,"event_time":"2026-01-03T12:00:20+00:00","arrival_time":"2026-01-03T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.21250755799999999,"normal":0.787492442},"reference_distribution":{"anomalous":0.4548836751106724,"normal":0.5451163248893276}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.787492442,"event_time":"2026-01-03T12:00:10+00:00","arrival_time":"2026-01-03T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.21250755799999999,"normal":0.787492442}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-03T12:00:10+00:00","arrival_time":"2026-01-03T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.787492442,"event_time":"2026-01-03T12:00:14+00:00","arrival_time":"2026-01-03T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.21250755799999999,"normal":0.787492442},"reference_distribution":{"anomalous":0.21250755799999999,"normal":0.787492442}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-03T12:00:14+00:00","arrival_time":"2026-01-03T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5451163248893276,"event_time":"2026-01-03T12:00:20+00:00","arrival_time":"2026-01-03T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.21250755799999999,"normal":0.787492442},"reference_distribution":{"anomalous":0.4548836751106724,"normal":0.5451163248893276}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-002-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-03T12:00:20+00:00","arrival_time":"2026-01-03T12:00:26+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":2,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"9ce643dc18465ff2d0d307af6db005fd8c01cfe47af39e6b8cbdc61344a3f4d2"}}
{"id":"evaluation-v1-contradiction_onset-20260725-003","name":"Evaluation v1.0 trajectory: contradiction_onset case 003","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-003","label":"Distractor 003","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8107,"modality":"semantic_status","timestamp":"2026-01-04T12:00:10Z","metadata":{"arrival_time":"2026-01-04T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-003","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-01-04T12:00:12Z","metadata":{"arrival_time":"2026-01-04T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.820525,"modality":"semantic_status","timestamp":"2026-01-04T12:00:20Z","metadata":{"arrival_time":"2026-01-04T12:00:27+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-04T12:00:10+00:00","obs-distractor":"2026-01-04T12:00:12+00:00","obs-2":"2026-01-04T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-04T12:00:10+00:00","obs-distractor":"2026-01-04T12:00:12+00:00","obs-2":"2026-01-04T12:00:27+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.934,"edge-ai-1":0.553},"confidence":{"obs-1":0.8107,"obs-distractor":0.63,"obs-2":0.820525},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-003-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5695040748090954,"event_time":"2026-01-04T12:00:20+00:00","arrival_time":"2026-01-04T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24926510000000002,"normal":0.7507349},"reference_distribution":{"anomalous":0.5695040748090954,"normal":0.4304959251909046}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7507349,"event_time":"2026-01-04T12:00:10+00:00","arrival_time":"2026-01-04T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.24926510000000002,"normal":0.7507349}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-04T12:00:10+00:00","arrival_time":"2026-01-04T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7507349,"event_time":"2026-01-04T12:00:12+00:00","arrival_time":"2026-01-04T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24926510000000002,"normal":0.7507349},"reference_distribution":{"anomalous":0.24926510000000002,"normal":0.7507349}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-04T12:00:12+00:00","arrival_time":"2026-01-04T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5695040748090954,"event_time":"2026-01-04T12:00:20+00:00","arrival_time":"2026-01-04T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24926510000000002,"normal":0.7507349},"reference_distribution":{"anomalous":0.5695040748090954,"normal":0.4304959251909046}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-003-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-04T12:00:20+00:00","arrival_time":"2026-01-04T12:00:27+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":3,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"3dd2527c96b45142a623c37184ec74800bb4138791684e597fb975b588793ade"}}
{"id":"evaluation-v1-contradiction_onset-20260725-004","name":"Evaluation v1.0 trajectory: contradiction_onset case 004","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-004","label":"Distractor 004","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.810933,"modality":"semantic_status","timestamp":"2026-01-05T12:00:10Z","metadata":{"arrival_time":"2026-01-05T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8207,"modality":"semantic_status","timestamp":"2026-01-05T12:00:20Z","metadata":{"arrival_time":"2026-01-05T12:00:28+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-004","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-01-05T12:00:13Z","metadata":{"arrival_time":"2026-01-05T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-05T12:00:10+00:00","obs-2":"2026-01-05T12:00:20+00:00","obs-distractor":"2026-01-05T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-05T12:00:10+00:00","obs-2":"2026-01-05T12:00:28+00:00","obs-distractor":"2026-01-05T12:00:13+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.942,"edge-ai-1":0.564},"confidence":{"obs-1":0.810933,"obs-2":0.8207,"obs-distractor":0.64},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-004-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5450065142019211,"event_time":"2026-01-05T12:00:20+00:00","arrival_time":"2026-01-05T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20710111399999998,"normal":0.792898886},"reference_distribution":{"anomalous":0.4549934857980789,"normal":0.5450065142019211}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.792898886,"event_time":"2026-01-05T12:00:10+00:00","arrival_time":"2026-01-05T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.20710111399999998,"normal":0.792898886}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-05T12:00:10+00:00","arrival_time":"2026-01-05T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.792898886,"event_time":"2026-01-05T12:00:13+00:00","arrival_time":"2026-01-05T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20710111399999998,"normal":0.792898886},"reference_distribution":{"anomalous":0.20710111399999998,"normal":0.792898886}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-05T12:00:13+00:00","arrival_time":"2026-01-05T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5450065142019211,"event_time":"2026-01-05T12:00:20+00:00","arrival_time":"2026-01-05T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20710111399999998,"normal":0.792898886},"reference_distribution":{"anomalous":0.4549934857980789,"normal":0.5450065142019211}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-004-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-05T12:00:20+00:00","arrival_time":"2026-01-05T12:00:28+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":4,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"b8dfe9c4f35ee1bc7dee64356b2e3f8a3b316755d475ba1c7e775608dbdb3f1b"}}
{"id":"evaluation-v1-contradiction_onset-20260725-005","name":"Evaluation v1.0 trajectory: contradiction_onset case 005","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-005","label":"Distractor 005","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.811167,"modality":"semantic_status","timestamp":"2026-01-06T12:00:10Z","metadata":{"arrival_time":"2026-01-06T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.820875,"modality":"semantic_status","timestamp":"2026-01-06T12:00:20Z","metadata":{"arrival_time":"2026-01-06T12:00:29+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-005","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-01-06T12:00:14Z","metadata":{"arrival_time":"2026-01-06T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-06T12:00:10+00:00","obs-2":"2026-01-06T12:00:20+00:00","obs-distractor":"2026-01-06T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-06T12:00:10+00:00","obs-2":"2026-01-06T12:00:29+00:00","obs-distractor":"2026-01-06T12:00:14+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.95,"edge-ai-1":0.575},"confidence":{"obs-1":0.811167,"obs-2":0.820875,"obs-distractor":0.65},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-005-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.570043110639408,"event_time":"2026-01-06T12:00:20+00:00","arrival_time":"2026-01-06T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.243287225,"normal":0.756712775},"reference_distribution":{"anomalous":0.570043110639408,"normal":0.4299568893605919}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.756712775,"event_time":"2026-01-06T12:00:10+00:00","arrival_time":"2026-01-06T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.243287225,"normal":0.756712775}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-06T12:00:10+00:00","arrival_time":"2026-01-06T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.756712775,"event_time":"2026-01-06T12:00:14+00:00","arrival_time":"2026-01-06T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.243287225,"normal":0.756712775},"reference_distribution":{"anomalous":0.243287225,"normal":0.756712775}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-06T12:00:14+00:00","arrival_time":"2026-01-06T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.570043110639408,"event_time":"2026-01-06T12:00:20+00:00","arrival_time":"2026-01-06T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.243287225,"normal":0.756712775},"reference_distribution":{"anomalous":0.570043110639408,"normal":0.4299568893605919}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-005-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-06T12:00:20+00:00","arrival_time":"2026-01-06T12:00:29+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":5,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"4a1e1c58ff28241c185c14703c3c964c01c7602ed50a359dccf754c8e7c6b7af"}}
{"id":"evaluation-v1-contradiction_onset-20260725-006","name":"Evaluation v1.0 trajectory: contradiction_onset case 006","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-006","label":"Distractor 006","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8114,"modality":"semantic_status","timestamp":"2026-01-07T12:00:10Z","metadata":{"arrival_time":"2026-01-07T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-006","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-01-07T12:00:12Z","metadata":{"arrival_time":"2026-01-07T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.82105,"modality":"semantic_status","timestamp":"2026-01-07T12:00:20Z","metadata":{"arrival_time":"2026-01-07T12:00:30+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-07T12:00:10+00:00","obs-distractor":"2026-01-07T12:00:12+00:00","obs-2":"2026-01-07T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-07T12:00:10+00:00","obs-distractor":"2026-01-07T12:00:12+00:00","obs-2":"2026-01-07T12:00:30+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.958,"edge-ai-1":0.586},"confidence":{"obs-1":0.8114,"obs-distractor":0.66,"obs-2":0.82105},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-006-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5449168193666213,"event_time":"2026-01-07T12:00:20+00:00","arrival_time":"2026-01-07T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20167880000000005,"normal":0.7983212},"reference_distribution":{"anomalous":0.45508318063337877,"normal":0.5449168193666213}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7983212,"event_time":"2026-01-07T12:00:10+00:00","arrival_time":"2026-01-07T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.20167880000000005,"normal":0.7983212}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-07T12:00:10+00:00","arrival_time":"2026-01-07T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7983212,"event_time":"2026-01-07T12:00:12+00:00","arrival_time":"2026-01-07T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20167880000000005,"normal":0.7983212},"reference_distribution":{"anomalous":0.20167880000000005,"normal":0.7983212}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-07T12:00:12+00:00","arrival_time":"2026-01-07T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5449168193666213,"event_time":"2026-01-07T12:00:20+00:00","arrival_time":"2026-01-07T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20167880000000005,"normal":0.7983212},"reference_distribution":{"anomalous":0.45508318063337877,"normal":0.5449168193666213}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-006-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-07T12:00:20+00:00","arrival_time":"2026-01-07T12:00:30+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":6,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"898cbc0d47eb095b1588a357a5e36b1e614c72af2e95a78bd447b010afe3157c"}}
{"id":"evaluation-v1-contradiction_onset-20260725-007","name":"Evaluation v1.0 trajectory: contradiction_onset case 007","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-007","label":"Distractor 007","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.811633,"modality":"semantic_status","timestamp":"2026-01-08T12:00:10Z","metadata":{"arrival_time":"2026-01-08T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-007","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-01-08T12:00:13Z","metadata":{"arrival_time":"2026-01-08T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.821225,"modality":"semantic_status","timestamp":"2026-01-08T12:00:20Z","metadata":{"arrival_time":"2026-01-08T12:00:31+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-08T12:00:10+00:00","obs-distractor":"2026-01-08T12:00:13+00:00","obs-2":"2026-01-08T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-08T12:00:10+00:00","obs-distractor":"2026-01-08T12:00:13+00:00","obs-2":"2026-01-08T12:00:31+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.966,"edge-ai-1":0.597},"confidence":{"obs-1":0.811633,"obs-distractor":0.67,"obs-2":0.821225},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-007-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5706261517065457,"event_time":"2026-01-08T12:00:20+00:00","arrival_time":"2026-01-08T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23729338099999997,"normal":0.762706619},"reference_distribution":{"anomalous":0.5706261517065457,"normal":0.42937384829345426}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.762706619,"event_time":"2026-01-08T12:00:10+00:00","arrival_time":"2026-01-08T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.23729338099999997,"normal":0.762706619}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-08T12:00:10+00:00","arrival_time":"2026-01-08T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.762706619,"event_time":"2026-01-08T12:00:13+00:00","arrival_time":"2026-01-08T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23729338099999997,"normal":0.762706619},"reference_distribution":{"anomalous":0.23729338099999997,"normal":0.762706619}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-08T12:00:13+00:00","arrival_time":"2026-01-08T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5706261517065457,"event_time":"2026-01-08T12:00:20+00:00","arrival_time":"2026-01-08T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23729338099999997,"normal":0.762706619},"reference_distribution":{"anomalous":0.5706261517065457,"normal":0.42937384829345426}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-007-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-08T12:00:20+00:00","arrival_time":"2026-01-08T12:00:31+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":7,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"f7a0dea5e10ff46396288fe07997f8f090d13cad4ea2e55db5ba3918cbac7b74"}}
{"id":"evaluation-v1-contradiction_onset-20260725-008","name":"Evaluation v1.0 trajectory: contradiction_onset case 008","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-008","label":"Distractor 008","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.811867,"modality":"semantic_status","timestamp":"2026-01-09T12:00:10Z","metadata":{"arrival_time":"2026-01-09T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-008","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-01-09T12:00:14Z","metadata":{"arrival_time":"2026-01-09T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8214,"modality":"semantic_status","timestamp":"2026-01-09T12:00:20Z","metadata":{"arrival_time":"2026-01-09T12:00:32+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-09T12:00:10+00:00","obs-distractor":"2026-01-09T12:00:14+00:00","obs-2":"2026-01-09T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-09T12:00:10+00:00","obs-distractor":"2026-01-09T12:00:14+00:00","obs-2":"2026-01-09T12:00:32+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.974,"edge-ai-1":0.608},"confidence":{"obs-1":0.811867,"obs-distractor":0.68,"obs-2":0.8214},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-008-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.544846966533303,"event_time":"2026-01-09T12:00:20+00:00","arrival_time":"2026-01-09T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.196241542,"normal":0.803758458},"reference_distribution":{"anomalous":0.45515303346669705,"normal":0.544846966533303}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.803758458,"event_time":"2026-01-09T12:00:10+00:00","arrival_time":"2026-01-09T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.196241542,"normal":0.803758458}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-09T12:00:10+00:00","arrival_time":"2026-01-09T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.803758458,"event_time":"2026-01-09T12:00:14+00:00","arrival_time":"2026-01-09T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.196241542,"normal":0.803758458},"reference_distribution":{"anomalous":0.196241542,"normal":0.803758458}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-09T12:00:14+00:00","arrival_time":"2026-01-09T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.544846966533303,"event_time":"2026-01-09T12:00:20+00:00","arrival_time":"2026-01-09T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.196241542,"normal":0.803758458},"reference_distribution":{"anomalous":0.45515303346669705,"normal":0.544846966533303}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-008-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-09T12:00:20+00:00","arrival_time":"2026-01-09T12:00:32+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":8,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"030c925921d2dca8fff002ccea70e8f624f4ddd2ac9a4595076086f4ea659828"}}
{"id":"evaluation-v1-contradiction_onset-20260725-009","name":"Evaluation v1.0 trajectory: contradiction_onset case 009","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-009","label":"Distractor 009","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8121,"modality":"semantic_status","timestamp":"2026-01-10T12:00:10Z","metadata":{"arrival_time":"2026-01-10T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.821575,"modality":"semantic_status","timestamp":"2026-01-10T12:00:20Z","metadata":{"arrival_time":"2026-01-10T12:00:33+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-009","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-01-10T12:00:12Z","metadata":{"arrival_time":"2026-01-10T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-10T12:00:10+00:00","obs-2":"2026-01-10T12:00:20+00:00","obs-distractor":"2026-01-10T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-10T12:00:10+00:00","obs-2":"2026-01-10T12:00:33+00:00","obs-distractor":"2026-01-10T12:00:12+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.91,"edge-ai-1":0.619},"confidence":{"obs-1":0.8121,"obs-2":0.821575,"obs-distractor":0.69},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-009-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5348893717424866,"event_time":"2026-01-10T12:00:20+00:00","arrival_time":"2026-01-10T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23128189999999993,"normal":0.7687181000000001},"reference_distribution":{"anomalous":0.5348893717424866,"normal":0.46511062825751337}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7687181000000001,"event_time":"2026-01-10T12:00:10+00:00","arrival_time":"2026-01-10T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.23128189999999993,"normal":0.7687181000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-10T12:00:10+00:00","arrival_time":"2026-01-10T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7687181000000001,"event_time":"2026-01-10T12:00:12+00:00","arrival_time":"2026-01-10T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23128189999999993,"normal":0.7687181000000001},"reference_distribution":{"anomalous":0.23128189999999993,"normal":0.7687181000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-10T12:00:12+00:00","arrival_time":"2026-01-10T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5348893717424866,"event_time":"2026-01-10T12:00:20+00:00","arrival_time":"2026-01-10T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23128189999999993,"normal":0.7687181000000001},"reference_distribution":{"anomalous":0.5348893717424866,"normal":0.46511062825751337}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-009-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-10T12:00:20+00:00","arrival_time":"2026-01-10T12:00:33+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":9,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"61cde9c0df79d26888390cc5a1181a8a9e6ed37612f54cf527f58865ca9e64f8"}}
{"id":"evaluation-v1-contradiction_onset-20260725-010","name":"Evaluation v1.0 trajectory: contradiction_onset case 010","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-010","label":"Distractor 010","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.812333,"modality":"semantic_status","timestamp":"2026-01-11T12:00:10Z","metadata":{"arrival_time":"2026-01-11T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.82175,"modality":"semantic_status","timestamp":"2026-01-11T12:00:20Z","metadata":{"arrival_time":"2026-01-11T12:00:34+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-010","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.7,"modality":"semantic_status","timestamp":"2026-01-11T12:00:13Z","metadata":{"arrival_time":"2026-01-11T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-11T12:00:10+00:00","obs-2":"2026-01-11T12:00:20+00:00","obs-distractor":"2026-01-11T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-11T12:00:10+00:00","obs-2":"2026-01-11T12:00:34+00:00","obs-distractor":"2026-01-11T12:00:13+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.918,"edge-ai-1":0.63},"confidence":{"obs-1":0.812333,"obs-2":0.82175,"obs-distractor":0.7},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-010-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5100141217851816,"event_time":"2026-01-11T12:00:20+00:00","arrival_time":"2026-01-11T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.21327830600000008,"normal":0.7867216939999999},"reference_distribution":{"anomalous":0.4899858782148184,"normal":0.5100141217851816}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7867216939999999,"event_time":"2026-01-11T12:00:10+00:00","arrival_time":"2026-01-11T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.21327830600000008,"normal":0.7867216939999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-11T12:00:10+00:00","arrival_time":"2026-01-11T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7867216939999999,"event_time":"2026-01-11T12:00:13+00:00","arrival_time":"2026-01-11T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.21327830600000008,"normal":0.7867216939999999},"reference_distribution":{"anomalous":0.21327830600000008,"normal":0.7867216939999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-11T12:00:13+00:00","arrival_time":"2026-01-11T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5100141217851816,"event_time":"2026-01-11T12:00:20+00:00","arrival_time":"2026-01-11T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.21327830600000008,"normal":0.7867216939999999},"reference_distribution":{"anomalous":0.4899858782148184,"normal":0.5100141217851816}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-010-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-11T12:00:20+00:00","arrival_time":"2026-01-11T12:00:34+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":10,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"f7c861ff24692e7095940affde94a5b1af47d8051ec872fb67986734a3a55167"}}
{"id":"evaluation-v1-contradiction_onset-20260725-011","name":"Evaluation v1.0 trajectory: contradiction_onset case 011","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-011","label":"Distractor 011","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.812567,"modality":"semantic_status","timestamp":"2026-01-12T12:00:10Z","metadata":{"arrival_time":"2026-01-12T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-011","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.71,"modality":"semantic_status","timestamp":"2026-01-12T12:00:14Z","metadata":{"arrival_time":"2026-01-12T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.821925,"modality":"semantic_status","timestamp":"2026-01-12T12:00:20Z","metadata":{"arrival_time":"2026-01-12T12:00:35+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-12T12:00:10+00:00","obs-distractor":"2026-01-12T12:00:14+00:00","obs-2":"2026-01-12T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-12T12:00:10+00:00","obs-distractor":"2026-01-12T12:00:14+00:00","obs-2":"2026-01-12T12:00:35+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.926,"edge-ai-1":0.641},"confidence":{"obs-1":0.812567,"obs-distractor":0.71,"obs-2":0.821925},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-011-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5765560859479583,"event_time":"2026-01-12T12:00:20+00:00","arrival_time":"2026-01-12T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.25619773999999995,"normal":0.74380226},"reference_distribution":{"anomalous":0.5765560859479583,"normal":0.42344391405204174}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.74380226,"event_time":"2026-01-12T12:00:10+00:00","arrival_time":"2026-01-12T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.25619773999999995,"normal":0.74380226}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-12T12:00:10+00:00","arrival_time":"2026-01-12T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.74380226,"event_time":"2026-01-12T12:00:14+00:00","arrival_time":"2026-01-12T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.25619773999999995,"normal":0.74380226},"reference_distribution":{"anomalous":0.25619773999999995,"normal":0.74380226}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-12T12:00:14+00:00","arrival_time":"2026-01-12T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5765560859479583,"event_time":"2026-01-12T12:00:20+00:00","arrival_time":"2026-01-12T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.25619773999999995,"normal":0.74380226},"reference_distribution":{"anomalous":0.5765560859479583,"normal":0.42344391405204174}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-011-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-12T12:00:20+00:00","arrival_time":"2026-01-12T12:00:35+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":11,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"57f959e624c6808bf1e6d021fd61ad112148e3a8e2616bb73aa6edba35565fa7"}}
{"id":"evaluation-v1-contradiction_onset-20260725-012","name":"Evaluation v1.0 trajectory: contradiction_onset case 012","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-012","label":"Distractor 012","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8128,"modality":"semantic_status","timestamp":"2026-01-13T12:00:10Z","metadata":{"arrival_time":"2026-01-13T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8221,"modality":"semantic_status","timestamp":"2026-01-13T12:00:20Z","metadata":{"arrival_time":"2026-01-13T12:00:36+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-012","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.72,"modality":"semantic_status","timestamp":"2026-01-13T12:00:12Z","metadata":{"arrival_time":"2026-01-13T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-13T12:00:10+00:00","obs-2":"2026-01-13T12:00:20+00:00","obs-distractor":"2026-01-13T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-13T12:00:10+00:00","obs-2":"2026-01-13T12:00:36+00:00","obs-distractor":"2026-01-13T12:00:12+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.934,"edge-ai-1":0.652},"confidence":{"obs-1":0.8128,"obs-2":0.8221,"obs-distractor":0.72},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-012-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5540792904973658,"event_time":"2026-01-13T12:00:20+00:00","arrival_time":"2026-01-13T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20784479999999994,"normal":0.7921552000000001},"reference_distribution":{"anomalous":0.4459207095026342,"normal":0.5540792904973658}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7921552000000001,"event_time":"2026-01-13T12:00:10+00:00","arrival_time":"2026-01-13T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.20784479999999994,"normal":0.7921552000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-13T12:00:10+00:00","arrival_time":"2026-01-13T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7921552000000001,"event_time":"2026-01-13T12:00:12+00:00","arrival_time":"2026-01-13T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20784479999999994,"normal":0.7921552000000001},"reference_distribution":{"anomalous":0.20784479999999994,"normal":0.7921552000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-13T12:00:12+00:00","arrival_time":"2026-01-13T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5540792904973658,"event_time":"2026-01-13T12:00:20+00:00","arrival_time":"2026-01-13T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20784479999999994,"normal":0.7921552000000001},"reference_distribution":{"anomalous":0.4459207095026342,"normal":0.5540792904973658}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-012-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-13T12:00:20+00:00","arrival_time":"2026-01-13T12:00:36+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":12,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"f4d8b057b1af1a401ffb9260de53616be044301ab13aadab41bf48c926e9528c"}}
{"id":"evaluation-v1-contradiction_onset-20260725-013","name":"Evaluation v1.0 trajectory: contradiction_onset case 013","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-013","label":"Distractor 013","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.813033,"modality":"semantic_status","timestamp":"2026-01-14T12:00:10Z","metadata":{"arrival_time":"2026-01-14T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-013","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.73,"modality":"semantic_status","timestamp":"2026-01-14T12:00:13Z","metadata":{"arrival_time":"2026-01-14T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.822275,"modality":"semantic_status","timestamp":"2026-01-14T12:00:20Z","metadata":{"arrival_time":"2026-01-14T12:00:37+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-14T12:00:10+00:00","obs-distractor":"2026-01-14T12:00:13+00:00","obs-2":"2026-01-14T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-14T12:00:10+00:00","obs-distractor":"2026-01-14T12:00:13+00:00","obs-2":"2026-01-14T12:00:37+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.942,"edge-ai-1":0.52},"confidence":{"obs-1":0.813033,"obs-distractor":0.73,"obs-2":0.822275},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-013-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5772008748638652,"event_time":"2026-01-14T12:00:20+00:00","arrival_time":"2026-01-14T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.250199666,"normal":0.749800334},"reference_distribution":{"anomalous":0.5772008748638652,"normal":0.4227991251361349}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.749800334,"event_time":"2026-01-14T12:00:10+00:00","arrival_time":"2026-01-14T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.250199666,"normal":0.749800334}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-14T12:00:10+00:00","arrival_time":"2026-01-14T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.749800334,"event_time":"2026-01-14T12:00:13+00:00","arrival_time":"2026-01-14T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.250199666,"normal":0.749800334},"reference_distribution":{"anomalous":0.250199666,"normal":0.749800334}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-14T12:00:13+00:00","arrival_time":"2026-01-14T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5772008748638652,"event_time":"2026-01-14T12:00:20+00:00","arrival_time":"2026-01-14T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.250199666,"normal":0.749800334},"reference_distribution":{"anomalous":0.5772008748638652,"normal":0.4227991251361349}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-013-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-14T12:00:20+00:00","arrival_time":"2026-01-14T12:00:37+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":13,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"90abc3ad488547d3cffe73f835db02e1cb8eeae306248df0ecf974ce701c1e26"}}
{"id":"evaluation-v1-contradiction_onset-20260725-014","name":"Evaluation v1.0 trajectory: contradiction_onset case 014","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-014","label":"Distractor 014","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.813267,"modality":"semantic_status","timestamp":"2026-01-15T12:00:10Z","metadata":{"arrival_time":"2026-01-15T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-014","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.74,"modality":"semantic_status","timestamp":"2026-01-15T12:00:14Z","metadata":{"arrival_time":"2026-01-15T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.82245,"modality":"semantic_status","timestamp":"2026-01-15T12:00:20Z","metadata":{"arrival_time":"2026-01-15T12:00:38+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-15T12:00:10+00:00","obs-distractor":"2026-01-15T12:00:14+00:00","obs-2":"2026-01-15T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-15T12:00:10+00:00","obs-distractor":"2026-01-15T12:00:14+00:00","obs-2":"2026-01-15T12:00:38+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.95,"edge-ai-1":0.531},"confidence":{"obs-1":0.813267,"obs-distractor":0.74,"obs-2":0.82245},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-014-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5541649874582167,"event_time":"2026-01-15T12:00:20+00:00","arrival_time":"2026-01-15T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2023963500000001,"normal":0.7976036499999999},"reference_distribution":{"anomalous":0.4458350125417833,"normal":0.5541649874582167}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7976036499999999,"event_time":"2026-01-15T12:00:10+00:00","arrival_time":"2026-01-15T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2023963500000001,"normal":0.7976036499999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-15T12:00:10+00:00","arrival_time":"2026-01-15T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7976036499999999,"event_time":"2026-01-15T12:00:14+00:00","arrival_time":"2026-01-15T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2023963500000001,"normal":0.7976036499999999},"reference_distribution":{"anomalous":0.2023963500000001,"normal":0.7976036499999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-15T12:00:14+00:00","arrival_time":"2026-01-15T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5541649874582167,"event_time":"2026-01-15T12:00:20+00:00","arrival_time":"2026-01-15T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2023963500000001,"normal":0.7976036499999999},"reference_distribution":{"anomalous":0.4458350125417833,"normal":0.5541649874582167}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-014-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-15T12:00:20+00:00","arrival_time":"2026-01-15T12:00:38+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":14,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"1bc8f8e15fd3ba869e13bfaf1da041274575eba1055af3d60ddc0eb758c1c678"}}
{"id":"evaluation-v1-contradiction_onset-20260725-015","name":"Evaluation v1.0 trajectory: contradiction_onset case 015","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-015","label":"Distractor 015","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8135,"modality":"semantic_status","timestamp":"2026-01-16T12:00:10Z","metadata":{"arrival_time":"2026-01-16T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-015","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.75,"modality":"semantic_status","timestamp":"2026-01-16T12:00:12Z","metadata":{"arrival_time":"2026-01-16T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.822625,"modality":"semantic_status","timestamp":"2026-01-16T12:00:20Z","metadata":{"arrival_time":"2026-01-16T12:00:39+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-16T12:00:10+00:00","obs-distractor":"2026-01-16T12:00:12+00:00","obs-2":"2026-01-16T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-16T12:00:10+00:00","obs-distractor":"2026-01-16T12:00:12+00:00","obs-2":"2026-01-16T12:00:39+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.958,"edge-ai-1":0.542},"confidence":{"obs-1":0.8135,"obs-distractor":0.75,"obs-2":0.822625},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-015-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5778938551658964,"event_time":"2026-01-16T12:00:20+00:00","arrival_time":"2026-01-16T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24418399999999996,"normal":0.755816},"reference_distribution":{"anomalous":0.5778938551658964,"normal":0.4221061448341036}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.755816,"event_time":"2026-01-16T12:00:10+00:00","arrival_time":"2026-01-16T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.24418399999999996,"normal":0.755816}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-16T12:00:10+00:00","arrival_time":"2026-01-16T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.755816,"event_time":"2026-01-16T12:00:12+00:00","arrival_time":"2026-01-16T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24418399999999996,"normal":0.755816},"reference_distribution":{"anomalous":0.24418399999999996,"normal":0.755816}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-16T12:00:12+00:00","arrival_time":"2026-01-16T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5778938551658964,"event_time":"2026-01-16T12:00:20+00:00","arrival_time":"2026-01-16T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24418399999999996,"normal":0.755816},"reference_distribution":{"anomalous":0.5778938551658964,"normal":0.4221061448341036}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-015-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-16T12:00:20+00:00","arrival_time":"2026-01-16T12:00:39+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":15,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"549bad929249ff071574749e460dda5e21097eb5ca136c3b119e6d5f64f11aec"}}
{"id":"evaluation-v1-contradiction_onset-20260725-016","name":"Evaluation v1.0 trajectory: contradiction_onset case 016","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-016","label":"Distractor 016","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.813733,"modality":"semantic_status","timestamp":"2026-01-17T12:00:10Z","metadata":{"arrival_time":"2026-01-17T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-016","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.76,"modality":"semantic_status","timestamp":"2026-01-17T12:00:13Z","metadata":{"arrival_time":"2026-01-17T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8228,"modality":"semantic_status","timestamp":"2026-01-17T12:00:20Z","metadata":{"arrival_time":"2026-01-17T12:00:40+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-17T12:00:10+00:00","obs-distractor":"2026-01-17T12:00:13+00:00","obs-2":"2026-01-17T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-17T12:00:10+00:00","obs-distractor":"2026-01-17T12:00:13+00:00","obs-2":"2026-01-17T12:00:40+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.966,"edge-ai-1":0.553},"confidence":{"obs-1":0.813733,"obs-distractor":0.76,"obs-2":0.8228},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-016-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5542796020931589,"event_time":"2026-01-17T12:00:20+00:00","arrival_time":"2026-01-17T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19693392199999993,"normal":0.8030660780000001},"reference_distribution":{"anomalous":0.4457203979068412,"normal":0.5542796020931589}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8030660780000001,"event_time":"2026-01-17T12:00:10+00:00","arrival_time":"2026-01-17T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.19693392199999993,"normal":0.8030660780000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-17T12:00:10+00:00","arrival_time":"2026-01-17T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8030660780000001,"event_time":"2026-01-17T12:00:13+00:00","arrival_time":"2026-01-17T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19693392199999993,"normal":0.8030660780000001},"reference_distribution":{"anomalous":0.19693392199999993,"normal":0.8030660780000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-17T12:00:13+00:00","arrival_time":"2026-01-17T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5542796020931589,"event_time":"2026-01-17T12:00:20+00:00","arrival_time":"2026-01-17T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19693392199999993,"normal":0.8030660780000001},"reference_distribution":{"anomalous":0.4457203979068412,"normal":0.5542796020931589}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-016-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-17T12:00:20+00:00","arrival_time":"2026-01-17T12:00:40+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":16,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"e513d4c421acc0f9f8025b43b18255ab22e7f3c670f346d2685b4f387229b01c"}}
{"id":"evaluation-v1-contradiction_onset-20260725-017","name":"Evaluation v1.0 trajectory: contradiction_onset case 017","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-017","label":"Distractor 017","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.813967,"modality":"semantic_status","timestamp":"2026-01-18T12:00:10Z","metadata":{"arrival_time":"2026-01-18T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.822975,"modality":"semantic_status","timestamp":"2026-01-18T12:00:20Z","metadata":{"arrival_time":"2026-01-18T12:00:24+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-017","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.77,"modality":"semantic_status","timestamp":"2026-01-18T12:00:14Z","metadata":{"arrival_time":"2026-01-18T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-18T12:00:10+00:00","obs-2":"2026-01-18T12:00:20+00:00","obs-distractor":"2026-01-18T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-18T12:00:10+00:00","obs-2":"2026-01-18T12:00:24+00:00","obs-distractor":"2026-01-18T12:00:14+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.974,"edge-ai-1":0.564},"confidence":{"obs-1":0.813967,"obs-2":0.822975,"obs-distractor":0.77},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-017-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5786400108929594,"event_time":"2026-01-18T12:00:20+00:00","arrival_time":"2026-01-18T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.238151522,"normal":0.761848478},"reference_distribution":{"anomalous":0.5786400108929594,"normal":0.42135998910704064}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.761848478,"event_time":"2026-01-18T12:00:10+00:00","arrival_time":"2026-01-18T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.238151522,"normal":0.761848478}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-18T12:00:10+00:00","arrival_time":"2026-01-18T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.761848478,"event_time":"2026-01-18T12:00:14+00:00","arrival_time":"2026-01-18T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.238151522,"normal":0.761848478},"reference_distribution":{"anomalous":0.238151522,"normal":0.761848478}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-18T12:00:14+00:00","arrival_time":"2026-01-18T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5786400108929594,"event_time":"2026-01-18T12:00:20+00:00","arrival_time":"2026-01-18T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.238151522,"normal":0.761848478},"reference_distribution":{"anomalous":0.5786400108929594,"normal":0.42135998910704064}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-017-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-18T12:00:20+00:00","arrival_time":"2026-01-18T12:00:24+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":17,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"a7911d5efae98823fa07444906e8c51aaf2b02c73d2bc9d18682214da21fceed"}}
{"id":"evaluation-v1-contradiction_onset-20260725-018","name":"Evaluation v1.0 trajectory: contradiction_onset case 018","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-018","label":"Distractor 018","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8142,"modality":"semantic_status","timestamp":"2026-01-19T12:00:10Z","metadata":{"arrival_time":"2026-01-19T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-018","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.78,"modality":"semantic_status","timestamp":"2026-01-19T12:00:12Z","metadata":{"arrival_time":"2026-01-19T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.82315,"modality":"semantic_status","timestamp":"2026-01-19T12:00:20Z","metadata":{"arrival_time":"2026-01-19T12:00:25+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-19T12:00:10+00:00","obs-distractor":"2026-01-19T12:00:12+00:00","obs-2":"2026-01-19T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-19T12:00:10+00:00","obs-distractor":"2026-01-19T12:00:12+00:00","obs-2":"2026-01-19T12:00:25+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.91,"edge-ai-1":0.575},"confidence":{"obs-1":0.8142,"obs-distractor":0.78,"obs-2":0.82315},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-018-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5196190173122317,"event_time":"2026-01-19T12:00:20+00:00","arrival_time":"2026-01-19T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.214078,"normal":0.785922},"reference_distribution":{"anomalous":0.48038098268776824,"normal":0.5196190173122317}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.785922,"event_time":"2026-01-19T12:00:10+00:00","arrival_time":"2026-01-19T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.214078,"normal":0.785922}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-19T12:00:10+00:00","arrival_time":"2026-01-19T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.785922,"event_time":"2026-01-19T12:00:12+00:00","arrival_time":"2026-01-19T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.214078,"normal":0.785922},"reference_distribution":{"anomalous":0.214078,"normal":0.785922}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-19T12:00:12+00:00","arrival_time":"2026-01-19T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5196190173122317,"event_time":"2026-01-19T12:00:20+00:00","arrival_time":"2026-01-19T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.214078,"normal":0.785922},"reference_distribution":{"anomalous":0.48038098268776824,"normal":0.5196190173122317}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-018-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-19T12:00:20+00:00","arrival_time":"2026-01-19T12:00:25+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":18,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"9071420465403d11c3f3de95ef33f45e43c50edf7eec31cf49f8c0c208ccfa6c"}}
{"id":"evaluation-v1-contradiction_onset-20260725-019","name":"Evaluation v1.0 trajectory: contradiction_onset case 019","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-019","label":"Distractor 019","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.814433,"modality":"semantic_status","timestamp":"2026-01-20T12:00:10Z","metadata":{"arrival_time":"2026-01-20T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-019","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.79,"modality":"semantic_status","timestamp":"2026-01-20T12:00:13Z","metadata":{"arrival_time":"2026-01-20T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.823325,"modality":"semantic_status","timestamp":"2026-01-20T12:00:20Z","metadata":{"arrival_time":"2026-01-20T12:00:26+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-20T12:00:10+00:00","obs-distractor":"2026-01-20T12:00:13+00:00","obs-2":"2026-01-20T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-20T12:00:10+00:00","obs-distractor":"2026-01-20T12:00:13+00:00","obs-2":"2026-01-20T12:00:26+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.918,"edge-ai-1":0.586},"confidence":{"obs-1":0.814433,"obs-distractor":0.79,"obs-2":0.823325},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-019-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.542401755577892,"event_time":"2026-01-20T12:00:20+00:00","arrival_time":"2026-01-20T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23210308400000002,"normal":0.767896916},"reference_distribution":{"anomalous":0.542401755577892,"normal":0.45759824442210795}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.767896916,"event_time":"2026-01-20T12:00:10+00:00","arrival_time":"2026-01-20T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.23210308400000002,"normal":0.767896916}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-20T12:00:10+00:00","arrival_time":"2026-01-20T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.767896916,"event_time":"2026-01-20T12:00:13+00:00","arrival_time":"2026-01-20T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23210308400000002,"normal":0.767896916},"reference_distribution":{"anomalous":0.23210308400000002,"normal":0.767896916}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-20T12:00:13+00:00","arrival_time":"2026-01-20T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.542401755577892,"event_time":"2026-01-20T12:00:20+00:00","arrival_time":"2026-01-20T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23210308400000002,"normal":0.767896916},"reference_distribution":{"anomalous":0.542401755577892,"normal":0.45759824442210795}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-019-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-20T12:00:20+00:00","arrival_time":"2026-01-20T12:00:26+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":19,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"748b7e914dff2b90954035a45a77998f6d2f680c62c6512c9b7dcd4c1343729c"}}
{"id":"evaluation-v1-contradiction_onset-20260725-020","name":"Evaluation v1.0 trajectory: contradiction_onset case 020","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-020","label":"Distractor 020","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.814667,"modality":"semantic_status","timestamp":"2026-01-21T12:00:10Z","metadata":{"arrival_time":"2026-01-21T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8235,"modality":"semantic_status","timestamp":"2026-01-21T12:00:20Z","metadata":{"arrival_time":"2026-01-21T12:00:27+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-020","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-01-21T12:00:14Z","metadata":{"arrival_time":"2026-01-21T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-21T12:00:10+00:00","obs-2":"2026-01-21T12:00:20+00:00","obs-distractor":"2026-01-21T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-21T12:00:10+00:00","obs-2":"2026-01-21T12:00:27+00:00","obs-distractor":"2026-01-21T12:00:14+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.926,"edge-ai-1":0.597},"confidence":{"obs-1":0.814667,"obs-2":0.8235,"obs-distractor":0.6},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-020-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5190240873737543,"event_time":"2026-01-21T12:00:20+00:00","arrival_time":"2026-01-21T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20861835799999995,"normal":0.791381642},"reference_distribution":{"anomalous":0.4809759126262457,"normal":0.5190240873737543}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.791381642,"event_time":"2026-01-21T12:00:10+00:00","arrival_time":"2026-01-21T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.20861835799999995,"normal":0.791381642}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-21T12:00:10+00:00","arrival_time":"2026-01-21T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.791381642,"event_time":"2026-01-21T12:00:14+00:00","arrival_time":"2026-01-21T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20861835799999995,"normal":0.791381642},"reference_distribution":{"anomalous":0.20861835799999995,"normal":0.791381642}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-21T12:00:14+00:00","arrival_time":"2026-01-21T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5190240873737543,"event_time":"2026-01-21T12:00:20+00:00","arrival_time":"2026-01-21T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20861835799999995,"normal":0.791381642},"reference_distribution":{"anomalous":0.4809759126262457,"normal":0.5190240873737543}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-020-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-21T12:00:20+00:00","arrival_time":"2026-01-21T12:00:27+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":20,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"3432ba9bc4a57377c8b89db26750b4739bd2386659c4bd862fb3bfdb9a08e00d"}}
{"id":"evaluation-v1-contradiction_onset-20260725-021","name":"Evaluation v1.0 trajectory: contradiction_onset case 021","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-021","label":"Distractor 021","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8149,"modality":"semantic_status","timestamp":"2026-01-22T12:00:10Z","metadata":{"arrival_time":"2026-01-22T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-021","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-01-22T12:00:12Z","metadata":{"arrival_time":"2026-01-22T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.823675,"modality":"semantic_status","timestamp":"2026-01-22T12:00:20Z","metadata":{"arrival_time":"2026-01-22T12:00:28+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-22T12:00:10+00:00","obs-distractor":"2026-01-22T12:00:12+00:00","obs-2":"2026-01-22T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-22T12:00:10+00:00","obs-distractor":"2026-01-22T12:00:12+00:00","obs-2":"2026-01-22T12:00:28+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.934,"edge-ai-1":0.608},"confidence":{"obs-1":0.8149,"obs-distractor":0.61,"obs-2":0.823675},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-021-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.542394217833009,"event_time":"2026-01-22T12:00:20+00:00","arrival_time":"2026-01-22T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22603700000000004,"normal":0.773963},"reference_distribution":{"anomalous":0.542394217833009,"normal":0.45760578216699105}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.773963,"event_time":"2026-01-22T12:00:10+00:00","arrival_time":"2026-01-22T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.22603700000000004,"normal":0.773963}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-22T12:00:10+00:00","arrival_time":"2026-01-22T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.773963,"event_time":"2026-01-22T12:00:12+00:00","arrival_time":"2026-01-22T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22603700000000004,"normal":0.773963},"reference_distribution":{"anomalous":0.22603700000000004,"normal":0.773963}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-22T12:00:12+00:00","arrival_time":"2026-01-22T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.542394217833009,"event_time":"2026-01-22T12:00:20+00:00","arrival_time":"2026-01-22T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22603700000000004,"normal":0.773963},"reference_distribution":{"anomalous":0.542394217833009,"normal":0.45760578216699105}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-021-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-22T12:00:20+00:00","arrival_time":"2026-01-22T12:00:28+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":21,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"45c50ed6e6c66dd9e331173c4a0b24cb2a4cb7295a2493b2757dcb297dbf93bb"}}
{"id":"evaluation-v1-contradiction_onset-20260725-022","name":"Evaluation v1.0 trajectory: contradiction_onset case 022","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-022","label":"Distractor 022","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.815133,"modality":"semantic_status","timestamp":"2026-01-23T12:00:10Z","metadata":{"arrival_time":"2026-01-23T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-022","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-01-23T12:00:13Z","metadata":{"arrival_time":"2026-01-23T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.82385,"modality":"semantic_status","timestamp":"2026-01-23T12:00:20Z","metadata":{"arrival_time":"2026-01-23T12:00:29+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-23T12:00:10+00:00","obs-distractor":"2026-01-23T12:00:13+00:00","obs-2":"2026-01-23T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-23T12:00:10+00:00","obs-distractor":"2026-01-23T12:00:13+00:00","obs-2":"2026-01-23T12:00:29+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.942,"edge-ai-1":0.619},"confidence":{"obs-1":0.815133,"obs-distractor":0.62,"obs-2":0.82385},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-022-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5632126879561412,"event_time":"2026-01-23T12:00:20+00:00","arrival_time":"2026-01-23T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.203144714,"normal":0.796855286},"reference_distribution":{"anomalous":0.43678731204385884,"normal":0.5632126879561412}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.796855286,"event_time":"2026-01-23T12:00:10+00:00","arrival_time":"2026-01-23T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.203144714,"normal":0.796855286}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-23T12:00:10+00:00","arrival_time":"2026-01-23T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.796855286,"event_time":"2026-01-23T12:00:13+00:00","arrival_time":"2026-01-23T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.203144714,"normal":0.796855286},"reference_distribution":{"anomalous":0.203144714,"normal":0.796855286}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-23T12:00:13+00:00","arrival_time":"2026-01-23T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5632126879561412,"event_time":"2026-01-23T12:00:20+00:00","arrival_time":"2026-01-23T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.203144714,"normal":0.796855286},"reference_distribution":{"anomalous":0.43678731204385884,"normal":0.5632126879561412}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-022-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-23T12:00:20+00:00","arrival_time":"2026-01-23T12:00:29+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":22,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"e0b9550bb3fdee9bc64200f77eab40ad072346033f690b8d9a719eb31dfea850"}}
{"id":"evaluation-v1-contradiction_onset-20260725-023","name":"Evaluation v1.0 trajectory: contradiction_onset case 023","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-023","label":"Distractor 023","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.815367,"modality":"semantic_status","timestamp":"2026-01-24T12:00:10Z","metadata":{"arrival_time":"2026-01-24T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-023","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-01-24T12:00:14Z","metadata":{"arrival_time":"2026-01-24T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.824025,"modality":"semantic_status","timestamp":"2026-01-24T12:00:20Z","metadata":{"arrival_time":"2026-01-24T12:00:30+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-24T12:00:10+00:00","obs-distractor":"2026-01-24T12:00:14+00:00","obs-2":"2026-01-24T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-24T12:00:10+00:00","obs-distractor":"2026-01-24T12:00:14+00:00","obs-2":"2026-01-24T12:00:30+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.95,"edge-ai-1":0.63},"confidence":{"obs-1":0.815367,"obs-distractor":0.63,"obs-2":0.824025},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-023-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.585059375759151,"event_time":"2026-01-24T12:00:20+00:00","arrival_time":"2026-01-24T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.251175437,"normal":0.748824563},"reference_distribution":{"anomalous":0.585059375759151,"normal":0.41494062424084893}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.748824563,"event_time":"2026-01-24T12:00:10+00:00","arrival_time":"2026-01-24T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.251175437,"normal":0.748824563}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-24T12:00:10+00:00","arrival_time":"2026-01-24T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.748824563,"event_time":"2026-01-24T12:00:14+00:00","arrival_time":"2026-01-24T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.251175437,"normal":0.748824563},"reference_distribution":{"anomalous":0.251175437,"normal":0.748824563}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-24T12:00:14+00:00","arrival_time":"2026-01-24T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.585059375759151,"event_time":"2026-01-24T12:00:20+00:00","arrival_time":"2026-01-24T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.251175437,"normal":0.748824563},"reference_distribution":{"anomalous":0.585059375759151,"normal":0.41494062424084893}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-023-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-24T12:00:20+00:00","arrival_time":"2026-01-24T12:00:30+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":23,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"a85a32953a4ac69887301709df9f751d9b91c83891b393d86cf47041b861a1fc"}}
{"id":"evaluation-v1-contradiction_onset-20260725-024","name":"Evaluation v1.0 trajectory: contradiction_onset case 024","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-024","label":"Distractor 024","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8156,"modality":"semantic_status","timestamp":"2026-01-25T12:00:10Z","metadata":{"arrival_time":"2026-01-25T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-024","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-01-25T12:00:12Z","metadata":{"arrival_time":"2026-01-25T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8242,"modality":"semantic_status","timestamp":"2026-01-25T12:00:20Z","metadata":{"arrival_time":"2026-01-25T12:00:31+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-25T12:00:10+00:00","obs-distractor":"2026-01-25T12:00:12+00:00","obs-2":"2026-01-25T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-25T12:00:10+00:00","obs-distractor":"2026-01-25T12:00:12+00:00","obs-2":"2026-01-25T12:00:31+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.958,"edge-ai-1":0.641},"confidence":{"obs-1":0.8156,"obs-distractor":0.64,"obs-2":0.8242},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-024-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5635016113174526,"event_time":"2026-01-25T12:00:20+00:00","arrival_time":"2026-01-25T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19765520000000003,"normal":0.8023448},"reference_distribution":{"anomalous":0.43649838868254737,"normal":0.5635016113174526}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8023448,"event_time":"2026-01-25T12:00:10+00:00","arrival_time":"2026-01-25T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.19765520000000003,"normal":0.8023448}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-25T12:00:10+00:00","arrival_time":"2026-01-25T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8023448,"event_time":"2026-01-25T12:00:12+00:00","arrival_time":"2026-01-25T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19765520000000003,"normal":0.8023448},"reference_distribution":{"anomalous":0.19765520000000003,"normal":0.8023448}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-25T12:00:12+00:00","arrival_time":"2026-01-25T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5635016113174526,"event_time":"2026-01-25T12:00:20+00:00","arrival_time":"2026-01-25T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19765520000000003,"normal":0.8023448},"reference_distribution":{"anomalous":0.43649838868254737,"normal":0.5635016113174526}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-024-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-25T12:00:20+00:00","arrival_time":"2026-01-25T12:00:31+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":24,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"192534836ba6f043763422516994a39303941694d78599c8c00d04c77af290db"}}
{"id":"evaluation-v1-contradiction_onset-20260725-025","name":"Evaluation v1.0 trajectory: contradiction_onset case 025","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-025","label":"Distractor 025","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.815833,"modality":"semantic_status","timestamp":"2026-01-26T12:00:10Z","metadata":{"arrival_time":"2026-01-26T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-025","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-01-26T12:00:13Z","metadata":{"arrival_time":"2026-01-26T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.824375,"modality":"semantic_status","timestamp":"2026-01-26T12:00:20Z","metadata":{"arrival_time":"2026-01-26T12:00:32+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-26T12:00:10+00:00","obs-distractor":"2026-01-26T12:00:13+00:00","obs-2":"2026-01-26T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-26T12:00:10+00:00","obs-distractor":"2026-01-26T12:00:13+00:00","obs-2":"2026-01-26T12:00:32+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.966,"edge-ai-1":0.652},"confidence":{"obs-1":0.815833,"obs-distractor":0.65,"obs-2":0.824375},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-025-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5859155357546878,"event_time":"2026-01-26T12:00:20+00:00","arrival_time":"2026-01-26T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24512276899999996,"normal":0.754877231},"reference_distribution":{"anomalous":0.5859155357546878,"normal":0.41408446424531214}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.754877231,"event_time":"2026-01-26T12:00:10+00:00","arrival_time":"2026-01-26T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.24512276899999996,"normal":0.754877231}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-26T12:00:10+00:00","arrival_time":"2026-01-26T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.754877231,"event_time":"2026-01-26T12:00:13+00:00","arrival_time":"2026-01-26T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24512276899999996,"normal":0.754877231},"reference_distribution":{"anomalous":0.24512276899999996,"normal":0.754877231}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-26T12:00:13+00:00","arrival_time":"2026-01-26T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5859155357546878,"event_time":"2026-01-26T12:00:20+00:00","arrival_time":"2026-01-26T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24512276899999996,"normal":0.754877231},"reference_distribution":{"anomalous":0.5859155357546878,"normal":0.41408446424531214}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-025-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-26T12:00:20+00:00","arrival_time":"2026-01-26T12:00:32+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":25,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"84b4020ed678db1a56d2b3447f6623f9e1e506e884eaaeeabb05270d8628a892"}}
{"id":"evaluation-v1-contradiction_onset-20260725-026","name":"Evaluation v1.0 trajectory: contradiction_onset case 026","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-026","label":"Distractor 026","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.816067,"modality":"semantic_status","timestamp":"2026-01-27T12:00:10Z","metadata":{"arrival_time":"2026-01-27T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-026","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-01-27T12:00:14Z","metadata":{"arrival_time":"2026-01-27T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.82455,"modality":"semantic_status","timestamp":"2026-01-27T12:00:20Z","metadata":{"arrival_time":"2026-01-27T12:00:33+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-27T12:00:10+00:00","obs-distractor":"2026-01-27T12:00:14+00:00","obs-2":"2026-01-27T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-27T12:00:10+00:00","obs-distractor":"2026-01-27T12:00:14+00:00","obs-2":"2026-01-27T12:00:33+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.974,"edge-ai-1":0.52},"confidence":{"obs-1":0.816067,"obs-distractor":0.66,"obs-2":0.82455},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-026-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5638334654161387,"event_time":"2026-01-27T12:00:20+00:00","arrival_time":"2026-01-27T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19215074200000004,"normal":0.807849258},"reference_distribution":{"anomalous":0.43616653458386134,"normal":0.5638334654161387}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.807849258,"event_time":"2026-01-27T12:00:10+00:00","arrival_time":"2026-01-27T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.19215074200000004,"normal":0.807849258}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-27T12:00:10+00:00","arrival_time":"2026-01-27T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.807849258,"event_time":"2026-01-27T12:00:14+00:00","arrival_time":"2026-01-27T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19215074200000004,"normal":0.807849258},"reference_distribution":{"anomalous":0.19215074200000004,"normal":0.807849258}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-27T12:00:14+00:00","arrival_time":"2026-01-27T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5638334654161387,"event_time":"2026-01-27T12:00:20+00:00","arrival_time":"2026-01-27T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19215074200000004,"normal":0.807849258},"reference_distribution":{"anomalous":0.43616653458386134,"normal":0.5638334654161387}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-026-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-27T12:00:20+00:00","arrival_time":"2026-01-27T12:00:33+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":26,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"291cec57ce5b36eedfeab96c20b069d942569fac9d49db84e70934c5dd2a6f7d"}}
{"id":"evaluation-v1-contradiction_onset-20260725-027","name":"Evaluation v1.0 trajectory: contradiction_onset case 027","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-027","label":"Distractor 027","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8163,"modality":"semantic_status","timestamp":"2026-01-28T12:00:10Z","metadata":{"arrival_time":"2026-01-28T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-027","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-01-28T12:00:12Z","metadata":{"arrival_time":"2026-01-28T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.824725,"modality":"semantic_status","timestamp":"2026-01-28T12:00:20Z","metadata":{"arrival_time":"2026-01-28T12:00:34+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-28T12:00:10+00:00","obs-distractor":"2026-01-28T12:00:12+00:00","obs-2":"2026-01-28T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-28T12:00:10+00:00","obs-distractor":"2026-01-28T12:00:12+00:00","obs-2":"2026-01-28T12:00:34+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.91,"edge-ai-1":0.531},"confidence":{"obs-1":0.8163,"obs-distractor":0.67,"obs-2":0.824725},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-027-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5499627425160456,"event_time":"2026-01-28T12:00:20+00:00","arrival_time":"2026-01-28T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2390525,"normal":0.7609475},"reference_distribution":{"anomalous":0.5499627425160456,"normal":0.4500372574839544}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7609475,"event_time":"2026-01-28T12:00:10+00:00","arrival_time":"2026-01-28T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2390525,"normal":0.7609475}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-28T12:00:10+00:00","arrival_time":"2026-01-28T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7609475,"event_time":"2026-01-28T12:00:12+00:00","arrival_time":"2026-01-28T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2390525,"normal":0.7609475},"reference_distribution":{"anomalous":0.2390525,"normal":0.7609475}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-28T12:00:12+00:00","arrival_time":"2026-01-28T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5499627425160456,"event_time":"2026-01-28T12:00:20+00:00","arrival_time":"2026-01-28T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2390525,"normal":0.7609475},"reference_distribution":{"anomalous":0.5499627425160456,"normal":0.4500372574839544}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-027-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-28T12:00:20+00:00","arrival_time":"2026-01-28T12:00:34+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":27,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"e535193fcd65da1752e1b3640d1e5ae08319ddc7a19d5bb10089ff593875ac71"}}
{"id":"evaluation-v1-contradiction_onset-20260725-028","name":"Evaluation v1.0 trajectory: contradiction_onset case 028","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-028","label":"Distractor 028","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.816533,"modality":"semantic_status","timestamp":"2026-01-29T12:00:10Z","metadata":{"arrival_time":"2026-01-29T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-028","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-01-29T12:00:13Z","metadata":{"arrival_time":"2026-01-29T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8249,"modality":"semantic_status","timestamp":"2026-01-29T12:00:20Z","metadata":{"arrival_time":"2026-01-29T12:00:35+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-29T12:00:10+00:00","obs-distractor":"2026-01-29T12:00:13+00:00","obs-2":"2026-01-29T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-29T12:00:10+00:00","obs-distractor":"2026-01-29T12:00:13+00:00","obs-2":"2026-01-29T12:00:35+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.918,"edge-ai-1":0.542},"confidence":{"obs-1":0.816533,"obs-distractor":0.68,"obs-2":0.8249},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-028-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5286265340263816,"event_time":"2026-01-29T12:00:20+00:00","arrival_time":"2026-01-29T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20942270600000001,"normal":0.790577294},"reference_distribution":{"anomalous":0.4713734659736184,"normal":0.5286265340263816}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.790577294,"event_time":"2026-01-29T12:00:10+00:00","arrival_time":"2026-01-29T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.20942270600000001,"normal":0.790577294}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-29T12:00:10+00:00","arrival_time":"2026-01-29T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.790577294,"event_time":"2026-01-29T12:00:13+00:00","arrival_time":"2026-01-29T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20942270600000001,"normal":0.790577294},"reference_distribution":{"anomalous":0.20942270600000001,"normal":0.790577294}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-29T12:00:13+00:00","arrival_time":"2026-01-29T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5286265340263816,"event_time":"2026-01-29T12:00:20+00:00","arrival_time":"2026-01-29T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20942270600000001,"normal":0.790577294},"reference_distribution":{"anomalous":0.4713734659736184,"normal":0.5286265340263816}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-028-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-29T12:00:20+00:00","arrival_time":"2026-01-29T12:00:35+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":28,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"f6feb511d37610e564058b5d6be3c200b88dd6f6f721ada5389385dd21c98490"}}
{"id":"evaluation-v1-contradiction_onset-20260725-029","name":"Evaluation v1.0 trajectory: contradiction_onset case 029","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-029","label":"Distractor 029","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.816767,"modality":"semantic_status","timestamp":"2026-01-30T12:00:10Z","metadata":{"arrival_time":"2026-01-30T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.825075,"modality":"semantic_status","timestamp":"2026-01-30T12:00:20Z","metadata":{"arrival_time":"2026-01-30T12:00:36+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-029","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-01-30T12:00:14Z","metadata":{"arrival_time":"2026-01-30T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-30T12:00:10+00:00","obs-2":"2026-01-30T12:00:20+00:00","obs-distractor":"2026-01-30T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-30T12:00:10+00:00","obs-2":"2026-01-30T12:00:36+00:00","obs-distractor":"2026-01-30T12:00:14+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.926,"edge-ai-1":0.553},"confidence":{"obs-1":0.816767,"obs-2":0.825075,"obs-distractor":0.69},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-029-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5500904823763639,"event_time":"2026-01-30T12:00:20+00:00","arrival_time":"2026-01-30T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.232965419,"normal":0.767034581},"reference_distribution":{"anomalous":0.5500904823763639,"normal":0.44990951762363607}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.767034581,"event_time":"2026-01-30T12:00:10+00:00","arrival_time":"2026-01-30T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.232965419,"normal":0.767034581}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-30T12:00:10+00:00","arrival_time":"2026-01-30T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.767034581,"event_time":"2026-01-30T12:00:14+00:00","arrival_time":"2026-01-30T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.232965419,"normal":0.767034581},"reference_distribution":{"anomalous":0.232965419,"normal":0.767034581}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-30T12:00:14+00:00","arrival_time":"2026-01-30T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5500904823763639,"event_time":"2026-01-30T12:00:20+00:00","arrival_time":"2026-01-30T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.232965419,"normal":0.767034581},"reference_distribution":{"anomalous":0.5500904823763639,"normal":0.44990951762363607}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-029-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-30T12:00:20+00:00","arrival_time":"2026-01-30T12:00:36+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":29,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"1712f01cf69ba3bb37b48014575a4a11c388c29fdfc4a73123672159898bc116"}}
{"id":"evaluation-v1-contradiction_onset-20260725-030","name":"Evaluation v1.0 trajectory: contradiction_onset case 030","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-030","label":"Distractor 030","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.817,"modality":"semantic_status","timestamp":"2026-01-31T12:00:10Z","metadata":{"arrival_time":"2026-01-31T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-030","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.7,"modality":"semantic_status","timestamp":"2026-01-31T12:00:12Z","metadata":{"arrival_time":"2026-01-31T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.82525,"modality":"semantic_status","timestamp":"2026-01-31T12:00:20Z","metadata":{"arrival_time":"2026-01-31T12:00:37+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-01-31T12:00:10+00:00","obs-distractor":"2026-01-31T12:00:12+00:00","obs-2":"2026-01-31T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-31T12:00:10+00:00","obs-distractor":"2026-01-31T12:00:12+00:00","obs-2":"2026-01-31T12:00:37+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.934,"edge-ai-1":0.564},"confidence":{"obs-1":0.817,"obs-distractor":0.7,"obs-2":0.82525},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-030-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5282296343216032,"event_time":"2026-01-31T12:00:20+00:00","arrival_time":"2026-01-31T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20392200000000005,"normal":0.796078},"reference_distribution":{"anomalous":0.4717703656783968,"normal":0.5282296343216032}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.796078,"event_time":"2026-01-31T12:00:10+00:00","arrival_time":"2026-01-31T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.20392200000000005,"normal":0.796078}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-31T12:00:10+00:00","arrival_time":"2026-01-31T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.796078,"event_time":"2026-01-31T12:00:12+00:00","arrival_time":"2026-01-31T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20392200000000005,"normal":0.796078},"reference_distribution":{"anomalous":0.20392200000000005,"normal":0.796078}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-31T12:00:12+00:00","arrival_time":"2026-01-31T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5282296343216032,"event_time":"2026-01-31T12:00:20+00:00","arrival_time":"2026-01-31T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20392200000000005,"normal":0.796078},"reference_distribution":{"anomalous":0.4717703656783968,"normal":0.5282296343216032}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-030-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-31T12:00:20+00:00","arrival_time":"2026-01-31T12:00:37+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":30,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"d520bad5a149d02f5c34bcef7e2ecafd30fbde30070e465648beca63b166c045"}}
{"id":"evaluation-v1-contradiction_onset-20260725-031","name":"Evaluation v1.0 trajectory: contradiction_onset case 031","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-031","label":"Distractor 031","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.817233,"modality":"semantic_status","timestamp":"2026-02-01T12:00:10Z","metadata":{"arrival_time":"2026-02-01T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.825425,"modality":"semantic_status","timestamp":"2026-02-01T12:00:20Z","metadata":{"arrival_time":"2026-02-01T12:00:38+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-031","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.71,"modality":"semantic_status","timestamp":"2026-02-01T12:00:13Z","metadata":{"arrival_time":"2026-02-01T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-01T12:00:10+00:00","obs-2":"2026-02-01T12:00:20+00:00","obs-distractor":"2026-02-01T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-01T12:00:10+00:00","obs-2":"2026-02-01T12:00:38+00:00","obs-distractor":"2026-02-01T12:00:13+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.942,"edge-ai-1":0.575},"confidence":{"obs-1":0.817233,"obs-2":0.825425,"obs-distractor":0.71},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-031-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5502388037292204,"event_time":"2026-02-01T12:00:20+00:00","arrival_time":"2026-02-01T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22686238699999994,"normal":0.7731376130000001},"reference_distribution":{"anomalous":0.5502388037292204,"normal":0.4497611962707796}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7731376130000001,"event_time":"2026-02-01T12:00:10+00:00","arrival_time":"2026-02-01T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.22686238699999994,"normal":0.7731376130000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-01T12:00:10+00:00","arrival_time":"2026-02-01T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7731376130000001,"event_time":"2026-02-01T12:00:13+00:00","arrival_time":"2026-02-01T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22686238699999994,"normal":0.7731376130000001},"reference_distribution":{"anomalous":0.22686238699999994,"normal":0.7731376130000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-01T12:00:13+00:00","arrival_time":"2026-02-01T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5502388037292204,"event_time":"2026-02-01T12:00:20+00:00","arrival_time":"2026-02-01T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22686238699999994,"normal":0.7731376130000001},"reference_distribution":{"anomalous":0.5502388037292204,"normal":0.4497611962707796}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-031-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-01T12:00:20+00:00","arrival_time":"2026-02-01T12:00:38+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":31,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"d95fddefbf9d761e7e625783d401de0bf1fe302e7d0bb3a8bd2896e58531dfb4"}}
{"id":"evaluation-v1-contradiction_onset-20260725-032","name":"Evaluation v1.0 trajectory: contradiction_onset case 032","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-032","label":"Distractor 032","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.817467,"modality":"semantic_status","timestamp":"2026-02-02T12:00:10Z","metadata":{"arrival_time":"2026-02-02T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-032","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.72,"modality":"semantic_status","timestamp":"2026-02-02T12:00:14Z","metadata":{"arrival_time":"2026-02-02T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8256,"modality":"semantic_status","timestamp":"2026-02-02T12:00:20Z","metadata":{"arrival_time":"2026-02-02T12:00:39+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-02-02T12:00:10+00:00","obs-distractor":"2026-02-02T12:00:14+00:00","obs-2":"2026-02-02T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-02T12:00:10+00:00","obs-distractor":"2026-02-02T12:00:14+00:00","obs-2":"2026-02-02T12:00:39+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.95,"edge-ai-1":0.586},"confidence":{"obs-1":0.817467,"obs-distractor":0.72,"obs-2":0.8256},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-032-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5278331227631317,"event_time":"2026-02-02T12:00:20+00:00","arrival_time":"2026-02-02T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19840634999999995,"normal":0.80159365},"reference_distribution":{"anomalous":0.47216687723686834,"normal":0.5278331227631317}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.80159365,"event_time":"2026-02-02T12:00:10+00:00","arrival_time":"2026-02-02T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.19840634999999995,"normal":0.80159365}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-02T12:00:10+00:00","arrival_time":"2026-02-02T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.80159365,"event_time":"2026-02-02T12:00:14+00:00","arrival_time":"2026-02-02T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19840634999999995,"normal":0.80159365},"reference_distribution":{"anomalous":0.19840634999999995,"normal":0.80159365}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-02T12:00:14+00:00","arrival_time":"2026-02-02T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5278331227631317,"event_time":"2026-02-02T12:00:20+00:00","arrival_time":"2026-02-02T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19840634999999995,"normal":0.80159365},"reference_distribution":{"anomalous":0.47216687723686834,"normal":0.5278331227631317}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-032-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-02T12:00:20+00:00","arrival_time":"2026-02-02T12:00:39+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":32,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"63930e594282758a0a4a22b74f4fd795d75d26fd4be1f624a8af37976cb8faa7"}}
{"id":"evaluation-v1-contradiction_onset-20260725-033","name":"Evaluation v1.0 trajectory: contradiction_onset case 033","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-033","label":"Distractor 033","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8177,"modality":"semantic_status","timestamp":"2026-02-03T12:00:10Z","metadata":{"arrival_time":"2026-02-03T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-033","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.73,"modality":"semantic_status","timestamp":"2026-02-03T12:00:12Z","metadata":{"arrival_time":"2026-02-03T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.825775,"modality":"semantic_status","timestamp":"2026-02-03T12:00:20Z","metadata":{"arrival_time":"2026-02-03T12:00:40+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-03T12:00:10+00:00","obs-distractor":"2026-02-03T12:00:12+00:00","obs-2":"2026-02-03T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-03T12:00:10+00:00","obs-distractor":"2026-02-03T12:00:12+00:00","obs-2":"2026-02-03T12:00:40+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.958,"edge-ai-1":0.597},"confidence":{"obs-1":0.8177,"obs-distractor":0.73,"obs-2":0.825775},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-033-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5930815583390963,"event_time":"2026-02-03T12:00:20+00:00","arrival_time":"2026-02-03T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.25219400000000003,"normal":0.747806},"reference_distribution":{"anomalous":0.5930815583390963,"normal":0.40691844166090374}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.747806,"event_time":"2026-02-03T12:00:10+00:00","arrival_time":"2026-02-03T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.25219400000000003,"normal":0.747806}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-03T12:00:10+00:00","arrival_time":"2026-02-03T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.747806,"event_time":"2026-02-03T12:00:12+00:00","arrival_time":"2026-02-03T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.25219400000000003,"normal":0.747806},"reference_distribution":{"anomalous":0.25219400000000003,"normal":0.747806}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-03T12:00:12+00:00","arrival_time":"2026-02-03T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5930815583390963,"event_time":"2026-02-03T12:00:20+00:00","arrival_time":"2026-02-03T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.25219400000000003,"normal":0.747806},"reference_distribution":{"anomalous":0.5930815583390963,"normal":0.40691844166090374}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-033-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-03T12:00:20+00:00","arrival_time":"2026-02-03T12:00:40+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":33,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"a0329cfe594f416ca7ae6e398fe96b80e718d11b495e86ffd3ce942fef56b8b5"}}
{"id":"evaluation-v1-contradiction_onset-20260725-034","name":"Evaluation v1.0 trajectory: contradiction_onset case 034","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-034","label":"Distractor 034","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.817933,"modality":"semantic_status","timestamp":"2026-02-04T12:00:10Z","metadata":{"arrival_time":"2026-02-04T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.82595,"modality":"semantic_status","timestamp":"2026-02-04T12:00:20Z","metadata":{"arrival_time":"2026-02-04T12:00:24+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-034","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.74,"modality":"semantic_status","timestamp":"2026-02-04T12:00:13Z","metadata":{"arrival_time":"2026-02-04T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-04T12:00:10+00:00","obs-2":"2026-02-04T12:00:20+00:00","obs-distractor":"2026-02-04T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-04T12:00:10+00:00","obs-2":"2026-02-04T12:00:24+00:00","obs-distractor":"2026-02-04T12:00:13+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.966,"edge-ai-1":0.608},"confidence":{"obs-1":0.817933,"obs-2":0.82595,"obs-distractor":0.74},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-034-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5730177482492643,"event_time":"2026-02-04T12:00:20+00:00","arrival_time":"2026-02-04T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19287672200000006,"normal":0.8071232779999999},"reference_distribution":{"anomalous":0.4269822517507356,"normal":0.5730177482492643}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8071232779999999,"event_time":"2026-02-04T12:00:10+00:00","arrival_time":"2026-02-04T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.19287672200000006,"normal":0.8071232779999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-04T12:00:10+00:00","arrival_time":"2026-02-04T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8071232779999999,"event_time":"2026-02-04T12:00:13+00:00","arrival_time":"2026-02-04T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19287672200000006,"normal":0.8071232779999999},"reference_distribution":{"anomalous":0.19287672200000006,"normal":0.8071232779999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-04T12:00:13+00:00","arrival_time":"2026-02-04T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5730177482492643,"event_time":"2026-02-04T12:00:20+00:00","arrival_time":"2026-02-04T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19287672200000006,"normal":0.8071232779999999},"reference_distribution":{"anomalous":0.4269822517507356,"normal":0.5730177482492643}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-034-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-04T12:00:20+00:00","arrival_time":"2026-02-04T12:00:24+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":34,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"67dba601835e4f69e88960546bbfdba56e3f212a93ebfecdfd2fee46e0de569e"}}
{"id":"evaluation-v1-contradiction_onset-20260725-035","name":"Evaluation v1.0 trajectory: contradiction_onset case 035","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-035","label":"Distractor 035","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.818167,"modality":"semantic_status","timestamp":"2026-02-05T12:00:10Z","metadata":{"arrival_time":"2026-02-05T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-035","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.75,"modality":"semantic_status","timestamp":"2026-02-05T12:00:14Z","metadata":{"arrival_time":"2026-02-05T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.826125,"modality":"semantic_status","timestamp":"2026-02-05T12:00:20Z","metadata":{"arrival_time":"2026-02-05T12:00:25+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-05T12:00:10+00:00","obs-distractor":"2026-02-05T12:00:14+00:00","obs-2":"2026-02-05T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-05T12:00:10+00:00","obs-distractor":"2026-02-05T12:00:14+00:00","obs-2":"2026-02-05T12:00:25+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.974,"edge-ai-1":0.619},"confidence":{"obs-1":0.818167,"obs-distractor":0.75,"obs-2":0.826125},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-035-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.594107253366213,"event_time":"2026-02-05T12:00:20+00:00","arrival_time":"2026-02-05T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24610273399999993,"normal":0.7538972660000001},"reference_distribution":{"anomalous":0.594107253366213,"normal":0.40589274663378705}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7538972660000001,"event_time":"2026-02-05T12:00:10+00:00","arrival_time":"2026-02-05T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.24610273399999993,"normal":0.7538972660000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-05T12:00:10+00:00","arrival_time":"2026-02-05T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7538972660000001,"event_time":"2026-02-05T12:00:14+00:00","arrival_time":"2026-02-05T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24610273399999993,"normal":0.7538972660000001},"reference_distribution":{"anomalous":0.24610273399999993,"normal":0.7538972660000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-05T12:00:14+00:00","arrival_time":"2026-02-05T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.594107253366213,"event_time":"2026-02-05T12:00:20+00:00","arrival_time":"2026-02-05T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24610273399999993,"normal":0.7538972660000001},"reference_distribution":{"anomalous":0.594107253366213,"normal":0.40589274663378705}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-035-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-05T12:00:20+00:00","arrival_time":"2026-02-05T12:00:25+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":35,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"99ece922102fd5fa3acb54db5472c63c8a8ce0e6ef5029bae8f5760209e391de"}}
{"id":"evaluation-v1-contradiction_onset-20260725-036","name":"Evaluation v1.0 trajectory: contradiction_onset case 036","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-036","label":"Distractor 036","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8184,"modality":"semantic_status","timestamp":"2026-02-06T12:00:10Z","metadata":{"arrival_time":"2026-02-06T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8263,"modality":"semantic_status","timestamp":"2026-02-06T12:00:20Z","metadata":{"arrival_time":"2026-02-06T12:00:26+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-036","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.76,"modality":"semantic_status","timestamp":"2026-02-06T12:00:12Z","metadata":{"arrival_time":"2026-02-06T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-06T12:00:10+00:00","obs-2":"2026-02-06T12:00:20+00:00","obs-distractor":"2026-02-06T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-06T12:00:10+00:00","obs-2":"2026-02-06T12:00:26+00:00","obs-distractor":"2026-02-06T12:00:12+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.91,"edge-ai-1":0.63},"confidence":{"obs-1":0.8184,"obs-2":0.8263,"obs-distractor":0.76},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-036-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5380244380053487,"event_time":"2026-02-06T12:00:20+00:00","arrival_time":"2026-02-06T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.210256,"normal":0.789744},"reference_distribution":{"anomalous":0.4619755619946513,"normal":0.5380244380053487}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.789744,"event_time":"2026-02-06T12:00:10+00:00","arrival_time":"2026-02-06T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.210256,"normal":0.789744}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-06T12:00:10+00:00","arrival_time":"2026-02-06T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.789744,"event_time":"2026-02-06T12:00:12+00:00","arrival_time":"2026-02-06T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.210256,"normal":0.789744},"reference_distribution":{"anomalous":0.210256,"normal":0.789744}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-06T12:00:12+00:00","arrival_time":"2026-02-06T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5380244380053487,"event_time":"2026-02-06T12:00:20+00:00","arrival_time":"2026-02-06T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.210256,"normal":0.789744},"reference_distribution":{"anomalous":0.4619755619946513,"normal":0.5380244380053487}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-036-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-06T12:00:20+00:00","arrival_time":"2026-02-06T12:00:26+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":36,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c97f2c4de8e4c943d3bccd44497272f7eb8e30853b5586d9123abff1a200db5c"}}
{"id":"evaluation-v1-contradiction_onset-20260725-037","name":"Evaluation v1.0 trajectory: contradiction_onset case 037","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-037","label":"Distractor 037","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.818633,"modality":"semantic_status","timestamp":"2026-02-07T12:00:10Z","metadata":{"arrival_time":"2026-02-07T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-037","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.77,"modality":"semantic_status","timestamp":"2026-02-07T12:00:13Z","metadata":{"arrival_time":"2026-02-07T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.826475,"modality":"semantic_status","timestamp":"2026-02-07T12:00:20Z","metadata":{"arrival_time":"2026-02-07T12:00:27+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-07T12:00:10+00:00","obs-distractor":"2026-02-07T12:00:13+00:00","obs-2":"2026-02-07T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-07T12:00:10+00:00","obs-distractor":"2026-02-07T12:00:13+00:00","obs-2":"2026-02-07T12:00:27+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.918,"edge-ai-1":0.641},"confidence":{"obs-1":0.818633,"obs-distractor":0.77,"obs-2":0.826475},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-037-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5576774457286886,"event_time":"2026-02-07T12:00:20+00:00","arrival_time":"2026-02-07T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23999547199999993,"normal":0.7600045280000001},"reference_distribution":{"anomalous":0.5576774457286886,"normal":0.44232255427131134}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7600045280000001,"event_time":"2026-02-07T12:00:10+00:00","arrival_time":"2026-02-07T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.23999547199999993,"normal":0.7600045280000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-07T12:00:10+00:00","arrival_time":"2026-02-07T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7600045280000001,"event_time":"2026-02-07T12:00:13+00:00","arrival_time":"2026-02-07T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23999547199999993,"normal":0.7600045280000001},"reference_distribution":{"anomalous":0.23999547199999993,"normal":0.7600045280000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-07T12:00:13+00:00","arrival_time":"2026-02-07T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5576774457286886,"event_time":"2026-02-07T12:00:20+00:00","arrival_time":"2026-02-07T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23999547199999993,"normal":0.7600045280000001},"reference_distribution":{"anomalous":0.5576774457286886,"normal":0.44232255427131134}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-037-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-07T12:00:20+00:00","arrival_time":"2026-02-07T12:00:27+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":37,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"8b2e2c2ab26ea9d50310710336703e2a61fcefed8cbb35df0abb2eb9e6f0ab6a"}}
{"id":"evaluation-v1-contradiction_onset-20260725-038","name":"Evaluation v1.0 trajectory: contradiction_onset case 038","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-038","label":"Distractor 038","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.818867,"modality":"semantic_status","timestamp":"2026-02-08T12:00:10Z","metadata":{"arrival_time":"2026-02-08T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-038","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.78,"modality":"semantic_status","timestamp":"2026-02-08T12:00:14Z","metadata":{"arrival_time":"2026-02-08T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.82665,"modality":"semantic_status","timestamp":"2026-02-08T12:00:20Z","metadata":{"arrival_time":"2026-02-08T12:00:28+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-02-08T12:00:10+00:00","obs-distractor":"2026-02-08T12:00:14+00:00","obs-2":"2026-02-08T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-08T12:00:10+00:00","obs-distractor":"2026-02-08T12:00:14+00:00","obs-2":"2026-02-08T12:00:28+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.926,"edge-ai-1":0.652},"confidence":{"obs-1":0.818867,"obs-distractor":0.78,"obs-2":0.82665},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-038-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5378231658786033,"event_time":"2026-02-08T12:00:20+00:00","arrival_time":"2026-02-08T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2047291579999999,"normal":0.7952708420000001},"reference_distribution":{"anomalous":0.46217683412139665,"normal":0.5378231658786033}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7952708420000001,"event_time":"2026-02-08T12:00:10+00:00","arrival_time":"2026-02-08T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2047291579999999,"normal":0.7952708420000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-08T12:00:10+00:00","arrival_time":"2026-02-08T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7952708420000001,"event_time":"2026-02-08T12:00:14+00:00","arrival_time":"2026-02-08T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2047291579999999,"normal":0.7952708420000001},"reference_distribution":{"anomalous":0.2047291579999999,"normal":0.7952708420000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-08T12:00:14+00:00","arrival_time":"2026-02-08T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5378231658786033,"event_time":"2026-02-08T12:00:20+00:00","arrival_time":"2026-02-08T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2047291579999999,"normal":0.7952708420000001},"reference_distribution":{"anomalous":0.46217683412139665,"normal":0.5378231658786033}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-038-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-08T12:00:20+00:00","arrival_time":"2026-02-08T12:00:28+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":38,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c11b2dfa2cec66f497fab707c61d34d92f74b02a503b01ad16a6ba987b84580f"}}
{"id":"evaluation-v1-contradiction_onset-20260725-039","name":"Evaluation v1.0 trajectory: contradiction_onset case 039","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-039","label":"Distractor 039","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8191,"modality":"semantic_status","timestamp":"2026-02-09T12:00:10Z","metadata":{"arrival_time":"2026-02-09T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.826825,"modality":"semantic_status","timestamp":"2026-02-09T12:00:20Z","metadata":{"arrival_time":"2026-02-09T12:00:29+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-039","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.79,"modality":"semantic_status","timestamp":"2026-02-09T12:00:12Z","metadata":{"arrival_time":"2026-02-09T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-09T12:00:10+00:00","obs-2":"2026-02-09T12:00:20+00:00","obs-distractor":"2026-02-09T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-09T12:00:10+00:00","obs-2":"2026-02-09T12:00:29+00:00","obs-distractor":"2026-02-09T12:00:12+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.934,"edge-ai-1":0.52},"confidence":{"obs-1":0.8191,"obs-2":0.826825,"obs-distractor":0.79},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-039-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5579587924200521,"event_time":"2026-02-09T12:00:20+00:00","arrival_time":"2026-02-09T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23387059999999993,"normal":0.7661294000000001},"reference_distribution":{"anomalous":0.5579587924200521,"normal":0.4420412075799479}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7661294000000001,"event_time":"2026-02-09T12:00:10+00:00","arrival_time":"2026-02-09T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.23387059999999993,"normal":0.7661294000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-09T12:00:10+00:00","arrival_time":"2026-02-09T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7661294000000001,"event_time":"2026-02-09T12:00:12+00:00","arrival_time":"2026-02-09T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23387059999999993,"normal":0.7661294000000001},"reference_distribution":{"anomalous":0.23387059999999993,"normal":0.7661294000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-09T12:00:12+00:00","arrival_time":"2026-02-09T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5579587924200521,"event_time":"2026-02-09T12:00:20+00:00","arrival_time":"2026-02-09T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23387059999999993,"normal":0.7661294000000001},"reference_distribution":{"anomalous":0.5579587924200521,"normal":0.4420412075799479}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-039-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-09T12:00:20+00:00","arrival_time":"2026-02-09T12:00:29+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":39,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"27e66d85d2c852e4b986b07eb9fea4a3119fdb3ca53b5d633f762c38516ebf76"}}
{"id":"evaluation-v1-contradiction_onset-20260725-040","name":"Evaluation v1.0 trajectory: contradiction_onset case 040","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-040","label":"Distractor 040","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.819333,"modality":"semantic_status","timestamp":"2026-02-10T12:00:10Z","metadata":{"arrival_time":"2026-02-10T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.827,"modality":"semantic_status","timestamp":"2026-02-10T12:00:20Z","metadata":{"arrival_time":"2026-02-10T12:00:30+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-040","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-02-10T12:00:13Z","metadata":{"arrival_time":"2026-02-10T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-10T12:00:10+00:00","obs-2":"2026-02-10T12:00:20+00:00","obs-distractor":"2026-02-10T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-10T12:00:10+00:00","obs-2":"2026-02-10T12:00:30+00:00","obs-distractor":"2026-02-10T12:00:13+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.942,"edge-ai-1":0.531},"confidence":{"obs-1":0.819333,"obs-2":0.827,"obs-distractor":0.6},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-040-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5376331616862965,"event_time":"2026-02-10T12:00:20+00:00","arrival_time":"2026-02-10T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19918831400000003,"normal":0.800811686},"reference_distribution":{"anomalous":0.4623668383137035,"normal":0.5376331616862965}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.800811686,"event_time":"2026-02-10T12:00:10+00:00","arrival_time":"2026-02-10T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.19918831400000003,"normal":0.800811686}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-10T12:00:10+00:00","arrival_time":"2026-02-10T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.800811686,"event_time":"2026-02-10T12:00:13+00:00","arrival_time":"2026-02-10T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19918831400000003,"normal":0.800811686},"reference_distribution":{"anomalous":0.19918831400000003,"normal":0.800811686}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-10T12:00:13+00:00","arrival_time":"2026-02-10T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5376331616862965,"event_time":"2026-02-10T12:00:20+00:00","arrival_time":"2026-02-10T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19918831400000003,"normal":0.800811686},"reference_distribution":{"anomalous":0.4623668383137035,"normal":0.5376331616862965}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-040-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-10T12:00:20+00:00","arrival_time":"2026-02-10T12:00:30+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":40,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"ef52bcc6d895edc017350333fe5e52050eccff31d179f2920093ac96d18b1190"}}
{"id":"evaluation-v1-contradiction_onset-20260725-041","name":"Evaluation v1.0 trajectory: contradiction_onset case 041","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-041","label":"Distractor 041","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.819567,"modality":"semantic_status","timestamp":"2026-02-11T12:00:10Z","metadata":{"arrival_time":"2026-02-11T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.827175,"modality":"semantic_status","timestamp":"2026-02-11T12:00:20Z","metadata":{"arrival_time":"2026-02-11T12:00:31+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-041","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-02-11T12:00:14Z","metadata":{"arrival_time":"2026-02-11T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-11T12:00:10+00:00","obs-2":"2026-02-11T12:00:20+00:00","obs-distractor":"2026-02-11T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-11T12:00:10+00:00","obs-2":"2026-02-11T12:00:31+00:00","obs-distractor":"2026-02-11T12:00:14+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.95,"edge-ai-1":0.542},"confidence":{"obs-1":0.819567,"obs-2":0.827175,"obs-distractor":0.61},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-041-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5582697864170267,"event_time":"2026-02-11T12:00:20+00:00","arrival_time":"2026-02-11T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.227728916,"normal":0.772271084},"reference_distribution":{"anomalous":0.5582697864170267,"normal":0.4417302135829733}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.772271084,"event_time":"2026-02-11T12:00:10+00:00","arrival_time":"2026-02-11T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.227728916,"normal":0.772271084}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-11T12:00:10+00:00","arrival_time":"2026-02-11T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.772271084,"event_time":"2026-02-11T12:00:14+00:00","arrival_time":"2026-02-11T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.227728916,"normal":0.772271084},"reference_distribution":{"anomalous":0.227728916,"normal":0.772271084}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-11T12:00:14+00:00","arrival_time":"2026-02-11T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5582697864170267,"event_time":"2026-02-11T12:00:20+00:00","arrival_time":"2026-02-11T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.227728916,"normal":0.772271084},"reference_distribution":{"anomalous":0.5582697864170267,"normal":0.4417302135829733}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-041-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-11T12:00:20+00:00","arrival_time":"2026-02-11T12:00:31+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":41,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"5d9381c43d1507e2cae406bb26fbd4b93f4a2c0302d44dfe412ae963097d0e1d"}}
{"id":"evaluation-v1-contradiction_onset-20260725-042","name":"Evaluation v1.0 trajectory: contradiction_onset case 042","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-042","label":"Distractor 042","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8198,"modality":"semantic_status","timestamp":"2026-02-12T12:00:10Z","metadata":{"arrival_time":"2026-02-12T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.82735,"modality":"semantic_status","timestamp":"2026-02-12T12:00:20Z","metadata":{"arrival_time":"2026-02-12T12:00:32+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-042","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-02-12T12:00:12Z","metadata":{"arrival_time":"2026-02-12T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-12T12:00:10+00:00","obs-2":"2026-02-12T12:00:20+00:00","obs-distractor":"2026-02-12T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-12T12:00:10+00:00","obs-2":"2026-02-12T12:00:32+00:00","obs-distractor":"2026-02-12T12:00:12+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.958,"edge-ai-1":0.553},"confidence":{"obs-1":0.8198,"obs-2":0.82735,"obs-distractor":0.62},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-042-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5374579350764744,"event_time":"2026-02-12T12:00:20+00:00","arrival_time":"2026-02-12T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19363160000000001,"normal":0.8063684},"reference_distribution":{"anomalous":0.46254206492352556,"normal":0.5374579350764744}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8063684,"event_time":"2026-02-12T12:00:10+00:00","arrival_time":"2026-02-12T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.19363160000000001,"normal":0.8063684}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-12T12:00:10+00:00","arrival_time":"2026-02-12T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8063684,"event_time":"2026-02-12T12:00:12+00:00","arrival_time":"2026-02-12T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19363160000000001,"normal":0.8063684},"reference_distribution":{"anomalous":0.19363160000000001,"normal":0.8063684}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-12T12:00:12+00:00","arrival_time":"2026-02-12T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5374579350764744,"event_time":"2026-02-12T12:00:20+00:00","arrival_time":"2026-02-12T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19363160000000001,"normal":0.8063684},"reference_distribution":{"anomalous":0.46254206492352556,"normal":0.5374579350764744}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-042-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-12T12:00:20+00:00","arrival_time":"2026-02-12T12:00:32+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":42,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"b2cce015f417520cae282738ba09fb5e76e8179386897e1544521206df79bfe5"}}
{"id":"evaluation-v1-contradiction_onset-20260725-043","name":"Evaluation v1.0 trajectory: contradiction_onset case 043","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-043","label":"Distractor 043","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.820033,"modality":"semantic_status","timestamp":"2026-02-13T12:00:10Z","metadata":{"arrival_time":"2026-02-13T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-043","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-02-13T12:00:13Z","metadata":{"arrival_time":"2026-02-13T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.827525,"modality":"semantic_status","timestamp":"2026-02-13T12:00:20Z","metadata":{"arrival_time":"2026-02-13T12:00:33+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-13T12:00:10+00:00","obs-distractor":"2026-02-13T12:00:13+00:00","obs-2":"2026-02-13T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-13T12:00:10+00:00","obs-distractor":"2026-02-13T12:00:13+00:00","obs-2":"2026-02-13T12:00:33+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.966,"edge-ai-1":0.564},"confidence":{"obs-1":0.820033,"obs-distractor":0.63,"obs-2":0.827525},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-043-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5586141488931641,"event_time":"2026-02-13T12:00:20+00:00","arrival_time":"2026-02-13T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22157128999999998,"normal":0.77842871},"reference_distribution":{"anomalous":0.5586141488931641,"normal":0.44138585110683587}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.77842871,"event_time":"2026-02-13T12:00:10+00:00","arrival_time":"2026-02-13T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.22157128999999998,"normal":0.77842871}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-13T12:00:10+00:00","arrival_time":"2026-02-13T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.77842871,"event_time":"2026-02-13T12:00:13+00:00","arrival_time":"2026-02-13T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22157128999999998,"normal":0.77842871},"reference_distribution":{"anomalous":0.22157128999999998,"normal":0.77842871}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-13T12:00:13+00:00","arrival_time":"2026-02-13T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5586141488931641,"event_time":"2026-02-13T12:00:20+00:00","arrival_time":"2026-02-13T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22157128999999998,"normal":0.77842871},"reference_distribution":{"anomalous":0.5586141488931641,"normal":0.44138585110683587}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-043-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-13T12:00:20+00:00","arrival_time":"2026-02-13T12:00:33+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":43,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"59343fbcf99362c895c593c89d8452e57fac9c4b59ded1d71af2800f22a2f4ba"}}
{"id":"evaluation-v1-contradiction_onset-20260725-044","name":"Evaluation v1.0 trajectory: contradiction_onset case 044","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-044","label":"Distractor 044","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.820267,"modality":"semantic_status","timestamp":"2026-02-14T12:00:10Z","metadata":{"arrival_time":"2026-02-14T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-044","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-02-14T12:00:14Z","metadata":{"arrival_time":"2026-02-14T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8277,"modality":"semantic_status","timestamp":"2026-02-14T12:00:20Z","metadata":{"arrival_time":"2026-02-14T12:00:34+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-02-14T12:00:10+00:00","obs-distractor":"2026-02-14T12:00:14+00:00","obs-2":"2026-02-14T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-14T12:00:10+00:00","obs-distractor":"2026-02-14T12:00:14+00:00","obs-2":"2026-02-14T12:00:34+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.974,"edge-ai-1":0.575},"confidence":{"obs-1":0.820267,"obs-distractor":0.64,"obs-2":0.8277},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-044-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5827146574172777,"event_time":"2026-02-14T12:00:20+00:00","arrival_time":"2026-02-14T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.18805994199999998,"normal":0.811940058},"reference_distribution":{"anomalous":0.41728534258272226,"normal":0.5827146574172777}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.811940058,"event_time":"2026-02-14T12:00:10+00:00","arrival_time":"2026-02-14T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.18805994199999998,"normal":0.811940058}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-14T12:00:10+00:00","arrival_time":"2026-02-14T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.811940058,"event_time":"2026-02-14T12:00:14+00:00","arrival_time":"2026-02-14T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.18805994199999998,"normal":0.811940058},"reference_distribution":{"anomalous":0.18805994199999998,"normal":0.811940058}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-14T12:00:14+00:00","arrival_time":"2026-02-14T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5827146574172777,"event_time":"2026-02-14T12:00:20+00:00","arrival_time":"2026-02-14T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.18805994199999998,"normal":0.811940058},"reference_distribution":{"anomalous":0.41728534258272226,"normal":0.5827146574172777}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-044-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-14T12:00:20+00:00","arrival_time":"2026-02-14T12:00:34+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":44,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"249697bb99df345b2338b3fb3c9261aaf57ff9fb62b08a6d139ba528654401e7"}}
{"id":"evaluation-v1-contradiction_onset-20260725-045","name":"Evaluation v1.0 trajectory: contradiction_onset case 045","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-045","label":"Distractor 045","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8205,"modality":"semantic_status","timestamp":"2026-02-15T12:00:10Z","metadata":{"arrival_time":"2026-02-15T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.827875,"modality":"semantic_status","timestamp":"2026-02-15T12:00:20Z","metadata":{"arrival_time":"2026-02-15T12:00:35+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-045","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-02-15T12:00:12Z","metadata":{"arrival_time":"2026-02-15T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-15T12:00:10+00:00","obs-2":"2026-02-15T12:00:20+00:00","obs-distractor":"2026-02-15T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-15T12:00:10+00:00","obs-2":"2026-02-15T12:00:35+00:00","obs-distractor":"2026-02-15T12:00:12+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.91,"edge-ai-1":0.586},"confidence":{"obs-1":0.8205,"obs-2":0.827875,"obs-distractor":0.65},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-045-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5651554651201683,"event_time":"2026-02-15T12:00:20+00:00","arrival_time":"2026-02-15T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2471255,"normal":0.7528745},"reference_distribution":{"anomalous":0.5651554651201683,"normal":0.4348445348798316}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7528745,"event_time":"2026-02-15T12:00:10+00:00","arrival_time":"2026-02-15T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2471255,"normal":0.7528745}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-15T12:00:10+00:00","arrival_time":"2026-02-15T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7528745,"event_time":"2026-02-15T12:00:12+00:00","arrival_time":"2026-02-15T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2471255,"normal":0.7528745},"reference_distribution":{"anomalous":0.2471255,"normal":0.7528745}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-15T12:00:12+00:00","arrival_time":"2026-02-15T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5651554651201683,"event_time":"2026-02-15T12:00:20+00:00","arrival_time":"2026-02-15T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2471255,"normal":0.7528745},"reference_distribution":{"anomalous":0.5651554651201683,"normal":0.4348445348798316}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-045-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-15T12:00:20+00:00","arrival_time":"2026-02-15T12:00:35+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":45,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"f01d6a133e4fb6ec42b5e11343f22d10bec28707325de37eabc9cbfa9b257776"}}
{"id":"evaluation-v1-contradiction_onset-20260725-046","name":"Evaluation v1.0 trajectory: contradiction_onset case 046","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-046","label":"Distractor 046","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.820733,"modality":"semantic_status","timestamp":"2026-02-16T12:00:10Z","metadata":{"arrival_time":"2026-02-16T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-046","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-02-16T12:00:13Z","metadata":{"arrival_time":"2026-02-16T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.82805,"modality":"semantic_status","timestamp":"2026-02-16T12:00:20Z","metadata":{"arrival_time":"2026-02-16T12:00:36+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1"},"event_times":{"obs-1":"2026-02-16T12:00:10+00:00","obs-distractor":"2026-02-16T12:00:13+00:00","obs-2":"2026-02-16T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-16T12:00:10+00:00","obs-distractor":"2026-02-16T12:00:13+00:00","obs-2":"2026-02-16T12:00:36+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.918,"edge-ai-1":0.597},"confidence":{"obs-1":0.820733,"obs-distractor":0.66,"obs-2":0.82805},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-046-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5472018519795683,"event_time":"2026-02-16T12:00:20+00:00","arrival_time":"2026-02-16T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20556710599999994,"normal":0.7944328940000001},"reference_distribution":{"anomalous":0.4527981480204317,"normal":0.5472018519795683}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.7944328940000001,"event_time":"2026-02-16T12:00:10+00:00","arrival_time":"2026-02-16T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.20556710599999994,"normal":0.7944328940000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-16T12:00:10+00:00","arrival_time":"2026-02-16T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7944328940000001,"event_time":"2026-02-16T12:00:13+00:00","arrival_time":"2026-02-16T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20556710599999994,"normal":0.7944328940000001},"reference_distribution":{"anomalous":0.20556710599999994,"normal":0.7944328940000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-16T12:00:13+00:00","arrival_time":"2026-02-16T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5472018519795683,"event_time":"2026-02-16T12:00:20+00:00","arrival_time":"2026-02-16T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20556710599999994,"normal":0.7944328940000001},"reference_distribution":{"anomalous":0.4527981480204317,"normal":0.5472018519795683}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-046-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-16T12:00:20+00:00","arrival_time":"2026-02-16T12:00:36+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":46,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"176b610313ae4a6c461cb699d036d9a55aec70674e129a53027aafeab86a05c2"}}
{"id":"evaluation-v1-contradiction_onset-20260725-047","name":"Evaluation v1.0 trajectory: contradiction_onset case 047","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-047","label":"Distractor 047","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.820967,"modality":"semantic_status","timestamp":"2026-02-17T12:00:10Z","metadata":{"arrival_time":"2026-02-17T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.828225,"modality":"semantic_status","timestamp":"2026-02-17T12:00:20Z","metadata":{"arrival_time":"2026-02-17T12:00:37+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-047","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-02-17T12:00:14Z","metadata":{"arrival_time":"2026-02-17T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-17T12:00:10+00:00","obs-2":"2026-02-17T12:00:20+00:00","obs-distractor":"2026-02-17T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-17T12:00:10+00:00","obs-2":"2026-02-17T12:00:37+00:00","obs-distractor":"2026-02-17T12:00:14+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.926,"edge-ai-1":0.608},"confidence":{"obs-1":0.820967,"obs-2":0.828225,"obs-distractor":0.67},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-047-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5655614742697711,"event_time":"2026-02-17T12:00:20+00:00","arrival_time":"2026-02-17T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24097963099999997,"normal":0.759020369},"reference_distribution":{"anomalous":0.5655614742697711,"normal":0.43443852573022895}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.759020369,"event_time":"2026-02-17T12:00:10+00:00","arrival_time":"2026-02-17T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.24097963099999997,"normal":0.759020369}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-17T12:00:10+00:00","arrival_time":"2026-02-17T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.759020369,"event_time":"2026-02-17T12:00:14+00:00","arrival_time":"2026-02-17T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24097963099999997,"normal":0.759020369},"reference_distribution":{"anomalous":0.24097963099999997,"normal":0.759020369}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-17T12:00:14+00:00","arrival_time":"2026-02-17T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5655614742697711,"event_time":"2026-02-17T12:00:20+00:00","arrival_time":"2026-02-17T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.24097963099999997,"normal":0.759020369},"reference_distribution":{"anomalous":0.5655614742697711,"normal":0.43443852573022895}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-047-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-17T12:00:20+00:00","arrival_time":"2026-02-17T12:00:37+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":47,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"ec8e22a4f2048a4c89fd4e147e36a5809fbfbe19e928fa84aaa13f4ea0e0f3ed"}}
{"id":"evaluation-v1-contradiction_onset-20260725-048","name":"Evaluation v1.0 trajectory: contradiction_onset case 048","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-048","label":"Distractor 048","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8212,"modality":"semantic_status","timestamp":"2026-02-18T12:00:10Z","metadata":{"arrival_time":"2026-02-18T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8284,"modality":"semantic_status","timestamp":"2026-02-18T12:00:20Z","metadata":{"arrival_time":"2026-02-18T12:00:38+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-048","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-02-18T12:00:12Z","metadata":{"arrival_time":"2026-02-18T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-18T12:00:10+00:00","obs-2":"2026-02-18T12:00:20+00:00","obs-distractor":"2026-02-18T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-18T12:00:10+00:00","obs-2":"2026-02-18T12:00:38+00:00","obs-distractor":"2026-02-18T12:00:12+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.934,"edge-ai-1":0.619},"confidence":{"obs-1":0.8212,"obs-2":0.8284,"obs-distractor":0.68},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-048-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5472066484261718,"event_time":"2026-02-18T12:00:20+00:00","arrival_time":"2026-02-18T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19999919999999993,"normal":0.8000008000000001},"reference_distribution":{"anomalous":0.4527933515738281,"normal":0.5472066484261718}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8000008000000001,"event_time":"2026-02-18T12:00:10+00:00","arrival_time":"2026-02-18T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.19999919999999993,"normal":0.8000008000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-18T12:00:10+00:00","arrival_time":"2026-02-18T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8000008000000001,"event_time":"2026-02-18T12:00:12+00:00","arrival_time":"2026-02-18T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19999919999999993,"normal":0.8000008000000001},"reference_distribution":{"anomalous":0.19999919999999993,"normal":0.8000008000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-18T12:00:12+00:00","arrival_time":"2026-02-18T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5472066484261718,"event_time":"2026-02-18T12:00:20+00:00","arrival_time":"2026-02-18T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19999919999999993,"normal":0.8000008000000001},"reference_distribution":{"anomalous":0.4527933515738281,"normal":0.5472066484261718}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-048-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-18T12:00:20+00:00","arrival_time":"2026-02-18T12:00:38+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":48,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"738293f8eb6898e2b339c4f756faf60e50be8c6511a7e4c93099a2b9f551ce41"}}
{"id":"evaluation-v1-contradiction_onset-20260725-049","name":"Evaluation v1.0 trajectory: contradiction_onset case 049","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-049","label":"Distractor 049","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.821433,"modality":"semantic_status","timestamp":"2026-02-19T12:00:10Z","metadata":{"arrival_time":"2026-02-19T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-049","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-02-19T12:00:13Z","metadata":{"arrival_time":"2026-02-19T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.828575,"modality":"semantic_status","timestamp":"2026-02-19T12:00:20Z","metadata":{"arrival_time":"2026-02-19T12:00:39+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-19T12:00:10+00:00","obs-distractor":"2026-02-19T12:00:13+00:00","obs-2":"2026-02-19T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-19T12:00:10+00:00","obs-distractor":"2026-02-19T12:00:13+00:00","obs-2":"2026-02-19T12:00:39+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.942,"edge-ai-1":0.63},"confidence":{"obs-1":0.821433,"obs-distractor":0.69,"obs-2":0.828575},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-049-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.56600620808735,"event_time":"2026-02-19T12:00:20+00:00","arrival_time":"2026-02-19T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.234817775,"normal":0.765182225},"reference_distribution":{"anomalous":0.56600620808735,"normal":0.4339937919126499}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.765182225,"event_time":"2026-02-19T12:00:10+00:00","arrival_time":"2026-02-19T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.234817775,"normal":0.765182225}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-19T12:00:10+00:00","arrival_time":"2026-02-19T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.765182225,"event_time":"2026-02-19T12:00:13+00:00","arrival_time":"2026-02-19T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.234817775,"normal":0.765182225},"reference_distribution":{"anomalous":0.234817775,"normal":0.765182225}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-19T12:00:13+00:00","arrival_time":"2026-02-19T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.56600620808735,"event_time":"2026-02-19T12:00:20+00:00","arrival_time":"2026-02-19T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.234817775,"normal":0.765182225},"reference_distribution":{"anomalous":0.56600620808735,"normal":0.4339937919126499}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_onset-20260725-049-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-19T12:00:20+00:00","arrival_time":"2026-02-19T12:00:39+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_onset","case_index":49,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"4cef75c6b74f83cb328fb1f2508458e7fc51b1de63af5ff4e6e6eb3a775cdadc"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-000","name":"Evaluation v1.0 trajectory: contradiction_resolution case 000","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-000","label":"Distractor 000","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.83,"modality":"semantic_status","timestamp":"2026-01-01T12:00:10Z","metadata":{"arrival_time":"2026-01-01T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.84,"modality":"semantic_status","timestamp":"2026-01-01T12:00:20Z","metadata":{"arrival_time":"2026-01-01T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96,"modality":"semantic_status","timestamp":"2026-01-01T12:00:30Z","metadata":{"arrival_time":"2026-01-01T12:00:34+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-000","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-01-01T12:00:12Z","metadata":{"arrival_time":"2026-01-01T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-01T12:00:10+00:00","obs-2":"2026-01-01T12:00:20+00:00","obs-3":"2026-01-01T12:00:30+00:00","obs-distractor":"2026-01-01T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-01T12:00:10+00:00","obs-2":"2026-01-01T12:00:20+00:00","obs-3":"2026-01-01T12:00:34+00:00","obs-distractor":"2026-01-01T12:00:12+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.91,"edge-ai-1":0.52},"confidence":{"obs-1":0.83,"obs-2":0.84,"obs-3":0.96,"obs-distractor":0.6},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9783665975895274,"event_time":"2026-01-01T12:00:30+00:00","arrival_time":"2026-01-01T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4484915629473603,"normal":0.5515084370526397},"reference_distribution":{"anomalous":0.02163340241047259,"normal":0.9783665975895274}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8003,"event_time":"2026-01-01T12:00:10+00:00","arrival_time":"2026-01-01T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1997,"normal":0.8003}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-01T12:00:10+00:00","arrival_time":"2026-01-01T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8003,"event_time":"2026-01-01T12:00:12+00:00","arrival_time":"2026-01-01T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1997,"normal":0.8003},"reference_distribution":{"anomalous":0.1997,"normal":0.8003}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-01T12:00:12+00:00","arrival_time":"2026-01-01T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5515084370526397,"event_time":"2026-01-01T12:00:20+00:00","arrival_time":"2026-01-01T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1997,"normal":0.8003},"reference_distribution":{"anomalous":0.4484915629473603,"normal":0.5515084370526397}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-000-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-01T12:00:20+00:00","arrival_time":"2026-01-01T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9783665975895274,"event_time":"2026-01-01T12:00:30+00:00","arrival_time":"2026-01-01T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4484915629473603,"normal":0.5515084370526397},"reference_distribution":{"anomalous":0.02163340241047259,"normal":0.9783665975895274}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-01T12:00:30+00:00","arrival_time":"2026-01-01T12:00:34+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":0,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"054080e03b82140d66effc695f5c05eac234f685e17d2f7bbe4b2a09a272b058"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-001","name":"Evaluation v1.0 trajectory: contradiction_resolution case 001","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-001","label":"Distractor 001","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.830175,"modality":"semantic_status","timestamp":"2026-01-02T12:00:10Z","metadata":{"arrival_time":"2026-01-02T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.840175,"modality":"semantic_status","timestamp":"2026-01-02T12:00:20Z","metadata":{"arrival_time":"2026-01-02T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95986,"modality":"semantic_status","timestamp":"2026-01-02T12:00:30Z","metadata":{"arrival_time":"2026-01-02T12:00:35+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-001","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-01-02T12:00:13Z","metadata":{"arrival_time":"2026-01-02T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-02T12:00:10+00:00","obs-2":"2026-01-02T12:00:20+00:00","obs-3":"2026-01-02T12:00:30+00:00","obs-distractor":"2026-01-02T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-02T12:00:10+00:00","obs-2":"2026-01-02T12:00:20+00:00","obs-3":"2026-01-02T12:00:35+00:00","obs-distractor":"2026-01-02T12:00:13+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.918,"edge-ai-1":0.531},"confidence":{"obs-1":0.830175,"obs-2":0.840175,"obs-3":0.95986,"obs-distractor":0.61},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9523232103608955,"event_time":"2026-01-02T12:00:30+00:00","arrival_time":"2026-01-02T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.576746332182604,"normal":0.42325366781739604},"reference_distribution":{"anomalous":0.04767678963910451,"normal":0.9523232103608955}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.760508075,"event_time":"2026-01-02T12:00:10+00:00","arrival_time":"2026-01-02T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.23949192500000005,"normal":0.760508075}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-02T12:00:10+00:00","arrival_time":"2026-01-02T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.760508075,"event_time":"2026-01-02T12:00:13+00:00","arrival_time":"2026-01-02T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23949192500000005,"normal":0.760508075},"reference_distribution":{"anomalous":0.23949192500000005,"normal":0.760508075}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-02T12:00:13+00:00","arrival_time":"2026-01-02T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.576746332182604,"event_time":"2026-01-02T12:00:20+00:00","arrival_time":"2026-01-02T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23949192500000005,"normal":0.760508075},"reference_distribution":{"anomalous":0.576746332182604,"normal":0.42325366781739604}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-001-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-02T12:00:20+00:00","arrival_time":"2026-01-02T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9523232103608955,"event_time":"2026-01-02T12:00:30+00:00","arrival_time":"2026-01-02T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.576746332182604,"normal":0.42325366781739604},"reference_distribution":{"anomalous":0.04767678963910451,"normal":0.9523232103608955}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-02T12:00:30+00:00","arrival_time":"2026-01-02T12:00:35+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":1,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"8834677475625c21979a03c69bfff1129c55de34dd853f9932eed615c5696c34"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-002","name":"Evaluation v1.0 trajectory: contradiction_resolution case 002","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-002","label":"Distractor 002","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.83035,"modality":"semantic_status","timestamp":"2026-01-03T12:00:10Z","metadata":{"arrival_time":"2026-01-03T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.84035,"modality":"semantic_status","timestamp":"2026-01-03T12:00:20Z","metadata":{"arrival_time":"2026-01-03T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95972,"modality":"semantic_status","timestamp":"2026-01-03T12:00:30Z","metadata":{"arrival_time":"2026-01-03T12:00:36+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-002","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-01-03T12:00:14Z","metadata":{"arrival_time":"2026-01-03T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-03T12:00:10+00:00","obs-2":"2026-01-03T12:00:20+00:00","obs-3":"2026-01-03T12:00:30+00:00","obs-distractor":"2026-01-03T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-03T12:00:10+00:00","obs-2":"2026-01-03T12:00:20+00:00","obs-3":"2026-01-03T12:00:36+00:00","obs-distractor":"2026-01-03T12:00:14+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.926,"edge-ai-1":0.542},"confidence":{"obs-1":0.83035,"obs-2":0.84035,"obs-3":0.95972,"obs-distractor":0.62},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9810359144105715,"event_time":"2026-01-03T12:00:30+00:00","arrival_time":"2026-01-03T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4486198683189213,"normal":0.5513801316810787},"reference_distribution":{"anomalous":0.01896408558942853,"normal":0.9810359144105715}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8059041,"event_time":"2026-01-03T12:00:10+00:00","arrival_time":"2026-01-03T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1940959,"normal":0.8059041}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-03T12:00:10+00:00","arrival_time":"2026-01-03T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8059041,"event_time":"2026-01-03T12:00:14+00:00","arrival_time":"2026-01-03T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1940959,"normal":0.8059041},"reference_distribution":{"anomalous":0.1940959,"normal":0.8059041}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-03T12:00:14+00:00","arrival_time":"2026-01-03T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5513801316810787,"event_time":"2026-01-03T12:00:20+00:00","arrival_time":"2026-01-03T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1940959,"normal":0.8059041},"reference_distribution":{"anomalous":0.4486198683189213,"normal":0.5513801316810787}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-002-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-03T12:00:20+00:00","arrival_time":"2026-01-03T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9810359144105715,"event_time":"2026-01-03T12:00:30+00:00","arrival_time":"2026-01-03T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4486198683189213,"normal":0.5513801316810787},"reference_distribution":{"anomalous":0.01896408558942853,"normal":0.9810359144105715}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-03T12:00:30+00:00","arrival_time":"2026-01-03T12:00:36+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":2,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"fb39e234258e7acf5fd5bd21f4f27e6034615b5ad506ebd9844902e1021b687f"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-003","name":"Evaluation v1.0 trajectory: contradiction_resolution case 003","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-003","label":"Distractor 003","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.830525,"modality":"semantic_status","timestamp":"2026-01-04T12:00:10Z","metadata":{"arrival_time":"2026-01-04T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-003","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-01-04T12:00:12Z","metadata":{"arrival_time":"2026-01-04T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.840525,"modality":"semantic_status","timestamp":"2026-01-04T12:00:20Z","metadata":{"arrival_time":"2026-01-04T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95958,"modality":"semantic_status","timestamp":"2026-01-04T12:00:30Z","metadata":{"arrival_time":"2026-01-04T12:00:37+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-01-04T12:00:10+00:00","obs-distractor":"2026-01-04T12:00:12+00:00","obs-2":"2026-01-04T12:00:20+00:00","obs-3":"2026-01-04T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-01-04T12:00:10+00:00","obs-distractor":"2026-01-04T12:00:12+00:00","obs-2":"2026-01-04T12:00:20+00:00","obs-3":"2026-01-04T12:00:37+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.934,"edge-ai-1":0.553},"confidence":{"obs-1":0.830525,"obs-distractor":0.63,"obs-2":0.840525,"obs-3":0.95958},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9568403326009783,"event_time":"2026-01-04T12:00:30+00:00","arrival_time":"2026-01-04T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5776747401256641,"normal":0.42232525987433583},"reference_distribution":{"anomalous":0.04315966739902174,"normal":0.9568403326009783}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.766733675,"event_time":"2026-01-04T12:00:10+00:00","arrival_time":"2026-01-04T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.233266325,"normal":0.766733675}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-04T12:00:10+00:00","arrival_time":"2026-01-04T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.766733675,"event_time":"2026-01-04T12:00:12+00:00","arrival_time":"2026-01-04T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.233266325,"normal":0.766733675},"reference_distribution":{"anomalous":0.233266325,"normal":0.766733675}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-04T12:00:12+00:00","arrival_time":"2026-01-04T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5776747401256641,"event_time":"2026-01-04T12:00:20+00:00","arrival_time":"2026-01-04T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.233266325,"normal":0.766733675},"reference_distribution":{"anomalous":0.5776747401256641,"normal":0.42232525987433583}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-003-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-04T12:00:20+00:00","arrival_time":"2026-01-04T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9568403326009783,"event_time":"2026-01-04T12:00:30+00:00","arrival_time":"2026-01-04T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5776747401256641,"normal":0.42232525987433583},"reference_distribution":{"anomalous":0.04315966739902174,"normal":0.9568403326009783}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-04T12:00:30+00:00","arrival_time":"2026-01-04T12:00:37+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":3,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c3d7db908b4089d4205d2e390ea6ba3ac5c29de76da884fee311c1d20a238f91"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-004","name":"Evaluation v1.0 trajectory: contradiction_resolution case 004","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-004","label":"Distractor 004","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8307,"modality":"semantic_status","timestamp":"2026-01-05T12:00:10Z","metadata":{"arrival_time":"2026-01-05T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-004","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-01-05T12:00:13Z","metadata":{"arrival_time":"2026-01-05T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8407,"modality":"semantic_status","timestamp":"2026-01-05T12:00:20Z","metadata":{"arrival_time":"2026-01-05T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95944,"modality":"semantic_status","timestamp":"2026-01-05T12:00:30Z","metadata":{"arrival_time":"2026-01-05T12:00:38+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-05T12:00:10+00:00","obs-distractor":"2026-01-05T12:00:13+00:00","obs-2":"2026-01-05T12:00:20+00:00","obs-3":"2026-01-05T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-01-05T12:00:10+00:00","obs-distractor":"2026-01-05T12:00:13+00:00","obs-2":"2026-01-05T12:00:20+00:00","obs-3":"2026-01-05T12:00:38+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.942,"edge-ai-1":0.564},"confidence":{"obs-1":0.8307,"obs-distractor":0.64,"obs-2":0.8407,"obs-3":0.95944},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.983541387412907,"event_time":"2026-01-05T12:00:30+00:00","arrival_time":"2026-01-05T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.44873101851108405,"normal":0.5512689814889159},"reference_distribution":{"anomalous":0.016458612587093035,"normal":0.983541387412907}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8115194,"event_time":"2026-01-05T12:00:10+00:00","arrival_time":"2026-01-05T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1884806,"normal":0.8115194}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-05T12:00:10+00:00","arrival_time":"2026-01-05T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8115194,"event_time":"2026-01-05T12:00:13+00:00","arrival_time":"2026-01-05T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1884806,"normal":0.8115194},"reference_distribution":{"anomalous":0.1884806,"normal":0.8115194}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-05T12:00:13+00:00","arrival_time":"2026-01-05T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5512689814889159,"event_time":"2026-01-05T12:00:20+00:00","arrival_time":"2026-01-05T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1884806,"normal":0.8115194},"reference_distribution":{"anomalous":0.44873101851108405,"normal":0.5512689814889159}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-004-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-05T12:00:20+00:00","arrival_time":"2026-01-05T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.983541387412907,"event_time":"2026-01-05T12:00:30+00:00","arrival_time":"2026-01-05T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.44873101851108405,"normal":0.5512689814889159},"reference_distribution":{"anomalous":0.016458612587093035,"normal":0.983541387412907}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-05T12:00:30+00:00","arrival_time":"2026-01-05T12:00:38+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":4,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"e9b946d86c6d66d5f8b98c67c6a372ee51316cbf70692186ec4910231117227c"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-005","name":"Evaluation v1.0 trajectory: contradiction_resolution case 005","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-005","label":"Distractor 005","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.830875,"modality":"semantic_status","timestamp":"2026-01-06T12:00:10Z","metadata":{"arrival_time":"2026-01-06T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.840875,"modality":"semantic_status","timestamp":"2026-01-06T12:00:20Z","metadata":{"arrival_time":"2026-01-06T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9593,"modality":"semantic_status","timestamp":"2026-01-06T12:00:30Z","metadata":{"arrival_time":"2026-01-06T12:00:39+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-005","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-01-06T12:00:14Z","metadata":{"arrival_time":"2026-01-06T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-06T12:00:10+00:00","obs-2":"2026-01-06T12:00:20+00:00","obs-3":"2026-01-06T12:00:30+00:00","obs-distractor":"2026-01-06T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-06T12:00:10+00:00","obs-2":"2026-01-06T12:00:20+00:00","obs-3":"2026-01-06T12:00:39+00:00","obs-distractor":"2026-01-06T12:00:14+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.95,"edge-ai-1":0.575},"confidence":{"obs-1":0.830875,"obs-2":0.840875,"obs-3":0.9593,"obs-distractor":0.65},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9611130994485018,"event_time":"2026-01-06T12:00:30+00:00","arrival_time":"2026-01-06T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5786794172309642,"normal":0.42132058276903583},"reference_distribution":{"anomalous":0.038886900551498245,"normal":0.9611130994485018}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7729718750000001,"event_time":"2026-01-06T12:00:10+00:00","arrival_time":"2026-01-06T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.22702812499999991,"normal":0.7729718750000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-06T12:00:10+00:00","arrival_time":"2026-01-06T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7729718750000001,"event_time":"2026-01-06T12:00:14+00:00","arrival_time":"2026-01-06T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22702812499999991,"normal":0.7729718750000001},"reference_distribution":{"anomalous":0.22702812499999991,"normal":0.7729718750000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-06T12:00:14+00:00","arrival_time":"2026-01-06T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5786794172309642,"event_time":"2026-01-06T12:00:20+00:00","arrival_time":"2026-01-06T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22702812499999991,"normal":0.7729718750000001},"reference_distribution":{"anomalous":0.5786794172309642,"normal":0.42132058276903583}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-005-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-06T12:00:20+00:00","arrival_time":"2026-01-06T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9611130994485018,"event_time":"2026-01-06T12:00:30+00:00","arrival_time":"2026-01-06T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5786794172309642,"normal":0.42132058276903583},"reference_distribution":{"anomalous":0.038886900551498245,"normal":0.9611130994485018}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-06T12:00:30+00:00","arrival_time":"2026-01-06T12:00:39+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":5,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"2a34cda5c215f47ec69dc96b4dc049bd9cefba7d48436563837d14ca77748104"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-006","name":"Evaluation v1.0 trajectory: contradiction_resolution case 006","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-006","label":"Distractor 006","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.83105,"modality":"semantic_status","timestamp":"2026-01-07T12:00:10Z","metadata":{"arrival_time":"2026-01-07T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.84105,"modality":"semantic_status","timestamp":"2026-01-07T12:00:20Z","metadata":{"arrival_time":"2026-01-07T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95916,"modality":"semantic_status","timestamp":"2026-01-07T12:00:30Z","metadata":{"arrival_time":"2026-01-07T12:00:40+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-006","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-01-07T12:00:12Z","metadata":{"arrival_time":"2026-01-07T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-07T12:00:10+00:00","obs-2":"2026-01-07T12:00:20+00:00","obs-3":"2026-01-07T12:00:30+00:00","obs-distractor":"2026-01-07T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-07T12:00:10+00:00","obs-2":"2026-01-07T12:00:20+00:00","obs-3":"2026-01-07T12:00:40+00:00","obs-distractor":"2026-01-07T12:00:12+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.958,"edge-ai-1":0.586},"confidence":{"obs-1":0.83105,"obs-2":0.84105,"obs-3":0.95916,"obs-distractor":0.66},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9858871366471716,"event_time":"2026-01-07T12:00:30+00:00","arrival_time":"2026-01-07T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.44882390637896613,"normal":0.5511760936210338},"reference_distribution":{"anomalous":0.01411286335282844,"normal":0.9858871366471716}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8171458999999999,"event_time":"2026-01-07T12:00:10+00:00","arrival_time":"2026-01-07T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.18285410000000013,"normal":0.8171458999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-07T12:00:10+00:00","arrival_time":"2026-01-07T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8171458999999999,"event_time":"2026-01-07T12:00:12+00:00","arrival_time":"2026-01-07T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.18285410000000013,"normal":0.8171458999999999},"reference_distribution":{"anomalous":0.18285410000000013,"normal":0.8171458999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-07T12:00:12+00:00","arrival_time":"2026-01-07T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5511760936210338,"event_time":"2026-01-07T12:00:20+00:00","arrival_time":"2026-01-07T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.18285410000000013,"normal":0.8171458999999999},"reference_distribution":{"anomalous":0.44882390637896613,"normal":0.5511760936210338}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-006-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-07T12:00:20+00:00","arrival_time":"2026-01-07T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9858871366471716,"event_time":"2026-01-07T12:00:30+00:00","arrival_time":"2026-01-07T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.44882390637896613,"normal":0.5511760936210338},"reference_distribution":{"anomalous":0.01411286335282844,"normal":0.9858871366471716}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-07T12:00:30+00:00","arrival_time":"2026-01-07T12:00:40+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":6,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c2007483c11e2f2fcc53a87db8415896f2f1bf51884f8fff8b3ce18c1e1e517b"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-007","name":"Evaluation v1.0 trajectory: contradiction_resolution case 007","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-007","label":"Distractor 007","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.831225,"modality":"semantic_status","timestamp":"2026-01-08T12:00:10Z","metadata":{"arrival_time":"2026-01-08T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-007","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-01-08T12:00:13Z","metadata":{"arrival_time":"2026-01-08T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.841225,"modality":"semantic_status","timestamp":"2026-01-08T12:00:20Z","metadata":{"arrival_time":"2026-01-08T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95902,"modality":"semantic_status","timestamp":"2026-01-08T12:00:30Z","metadata":{"arrival_time":"2026-01-08T12:00:41+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-01-08T12:00:10+00:00","obs-distractor":"2026-01-08T12:00:13+00:00","obs-2":"2026-01-08T12:00:20+00:00","obs-3":"2026-01-08T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-01-08T12:00:10+00:00","obs-distractor":"2026-01-08T12:00:13+00:00","obs-2":"2026-01-08T12:00:20+00:00","obs-3":"2026-01-08T12:00:41+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.966,"edge-ai-1":0.597},"confidence":{"obs-1":0.831225,"obs-distractor":0.67,"obs-2":0.841225,"obs-3":0.95902},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9651469307795691,"event_time":"2026-01-08T12:00:30+00:00","arrival_time":"2026-01-08T12:00:41+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5797672462958291,"normal":0.4202327537041709},"reference_distribution":{"anomalous":0.03485306922043076,"normal":0.9651469307795691}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.779222675,"event_time":"2026-01-08T12:00:10+00:00","arrival_time":"2026-01-08T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.22077732500000002,"normal":0.779222675}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-08T12:00:10+00:00","arrival_time":"2026-01-08T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.779222675,"event_time":"2026-01-08T12:00:13+00:00","arrival_time":"2026-01-08T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22077732500000002,"normal":0.779222675},"reference_distribution":{"anomalous":0.22077732500000002,"normal":0.779222675}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-08T12:00:13+00:00","arrival_time":"2026-01-08T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5797672462958291,"event_time":"2026-01-08T12:00:20+00:00","arrival_time":"2026-01-08T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22077732500000002,"normal":0.779222675},"reference_distribution":{"anomalous":0.5797672462958291,"normal":0.4202327537041709}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-007-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-08T12:00:20+00:00","arrival_time":"2026-01-08T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9651469307795691,"event_time":"2026-01-08T12:00:30+00:00","arrival_time":"2026-01-08T12:00:41+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5797672462958291,"normal":0.4202327537041709},"reference_distribution":{"anomalous":0.03485306922043076,"normal":0.9651469307795691}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-08T12:00:30+00:00","arrival_time":"2026-01-08T12:00:41+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":7,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"827306c734bfe0db99d1fab087fd8139e0a17e1393f35a5dac2764a467cf5e0c"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-008","name":"Evaluation v1.0 trajectory: contradiction_resolution case 008","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-008","label":"Distractor 008","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8314,"modality":"semantic_status","timestamp":"2026-01-09T12:00:10Z","metadata":{"arrival_time":"2026-01-09T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-008","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-01-09T12:00:14Z","metadata":{"arrival_time":"2026-01-09T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8414,"modality":"semantic_status","timestamp":"2026-01-09T12:00:20Z","metadata":{"arrival_time":"2026-01-09T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95888,"modality":"semantic_status","timestamp":"2026-01-09T12:00:30Z","metadata":{"arrival_time":"2026-01-09T12:00:42+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-09T12:00:10+00:00","obs-distractor":"2026-01-09T12:00:14+00:00","obs-2":"2026-01-09T12:00:20+00:00","obs-3":"2026-01-09T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-01-09T12:00:10+00:00","obs-distractor":"2026-01-09T12:00:14+00:00","obs-2":"2026-01-09T12:00:20+00:00","obs-3":"2026-01-09T12:00:42+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.974,"edge-ai-1":0.608},"confidence":{"obs-1":0.8314,"obs-distractor":0.68,"obs-2":0.8414,"obs-3":0.95888},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9880772854462787,"event_time":"2026-01-09T12:00:30+00:00","arrival_time":"2026-01-09T12:00:42+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4488972689772057,"normal":0.5511027310227943},"reference_distribution":{"anomalous":0.011922714553721266,"normal":0.9880772854462787}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8227836,"event_time":"2026-01-09T12:00:10+00:00","arrival_time":"2026-01-09T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.17721640000000005,"normal":0.8227836}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-09T12:00:10+00:00","arrival_time":"2026-01-09T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8227836,"event_time":"2026-01-09T12:00:14+00:00","arrival_time":"2026-01-09T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.17721640000000005,"normal":0.8227836},"reference_distribution":{"anomalous":0.17721640000000005,"normal":0.8227836}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-09T12:00:14+00:00","arrival_time":"2026-01-09T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5511027310227943,"event_time":"2026-01-09T12:00:20+00:00","arrival_time":"2026-01-09T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.17721640000000005,"normal":0.8227836},"reference_distribution":{"anomalous":0.4488972689772057,"normal":0.5511027310227943}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-008-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-09T12:00:20+00:00","arrival_time":"2026-01-09T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9880772854462787,"event_time":"2026-01-09T12:00:30+00:00","arrival_time":"2026-01-09T12:00:42+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4488972689772057,"normal":0.5511027310227943},"reference_distribution":{"anomalous":0.011922714553721266,"normal":0.9880772854462787}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-09T12:00:30+00:00","arrival_time":"2026-01-09T12:00:42+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":8,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"4c0b2377edbaea1efea3350270a44cbc934cde75eba8b5e73840442c44dd1f65"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-009","name":"Evaluation v1.0 trajectory: contradiction_resolution case 009","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-009","label":"Distractor 009","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.831575,"modality":"semantic_status","timestamp":"2026-01-10T12:00:10Z","metadata":{"arrival_time":"2026-01-10T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.841575,"modality":"semantic_status","timestamp":"2026-01-10T12:00:20Z","metadata":{"arrival_time":"2026-01-10T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95874,"modality":"semantic_status","timestamp":"2026-01-10T12:00:30Z","metadata":{"arrival_time":"2026-01-10T12:00:43+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-009","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-01-10T12:00:12Z","metadata":{"arrival_time":"2026-01-10T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-10T12:00:10+00:00","obs-2":"2026-01-10T12:00:20+00:00","obs-3":"2026-01-10T12:00:30+00:00","obs-distractor":"2026-01-10T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-10T12:00:10+00:00","obs-2":"2026-01-10T12:00:20+00:00","obs-3":"2026-01-10T12:00:43+00:00","obs-distractor":"2026-01-10T12:00:12+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.91,"edge-ai-1":0.619},"confidence":{"obs-1":0.831575,"obs-2":0.841575,"obs-3":0.95874,"obs-distractor":0.69},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9689473742969307,"event_time":"2026-01-10T12:00:30+00:00","arrival_time":"2026-01-10T12:00:43+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5392951590144084,"normal":0.4607048409855916},"reference_distribution":{"anomalous":0.031052625703069298,"normal":0.9689473742969307}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7854860749999999,"event_time":"2026-01-10T12:00:10+00:00","arrival_time":"2026-01-10T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2145139250000001,"normal":0.7854860749999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-10T12:00:10+00:00","arrival_time":"2026-01-10T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7854860749999999,"event_time":"2026-01-10T12:00:12+00:00","arrival_time":"2026-01-10T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2145139250000001,"normal":0.7854860749999999},"reference_distribution":{"anomalous":0.2145139250000001,"normal":0.7854860749999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-10T12:00:12+00:00","arrival_time":"2026-01-10T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5392951590144084,"event_time":"2026-01-10T12:00:20+00:00","arrival_time":"2026-01-10T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2145139250000001,"normal":0.7854860749999999},"reference_distribution":{"anomalous":0.5392951590144084,"normal":0.4607048409855916}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-009-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-10T12:00:20+00:00","arrival_time":"2026-01-10T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9689473742969307,"event_time":"2026-01-10T12:00:30+00:00","arrival_time":"2026-01-10T12:00:43+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5392951590144084,"normal":0.4607048409855916},"reference_distribution":{"anomalous":0.031052625703069298,"normal":0.9689473742969307}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-10T12:00:30+00:00","arrival_time":"2026-01-10T12:00:43+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":9,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"ccffb61c5af726937ff4bcff1db2db5c4be97dbca8fe96edf5a344ebbbf2d975"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-010","name":"Evaluation v1.0 trajectory: contradiction_resolution case 010","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-010","label":"Distractor 010","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.83175,"modality":"semantic_status","timestamp":"2026-01-11T12:00:10Z","metadata":{"arrival_time":"2026-01-11T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-010","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.7,"modality":"semantic_status","timestamp":"2026-01-11T12:00:13Z","metadata":{"arrival_time":"2026-01-11T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.84175,"modality":"semantic_status","timestamp":"2026-01-11T12:00:20Z","metadata":{"arrival_time":"2026-01-11T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9586,"modality":"semantic_status","timestamp":"2026-01-11T12:00:30Z","metadata":{"arrival_time":"2026-01-11T12:00:44+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-11T12:00:10+00:00","obs-distractor":"2026-01-11T12:00:13+00:00","obs-2":"2026-01-11T12:00:20+00:00","obs-3":"2026-01-11T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-01-11T12:00:10+00:00","obs-distractor":"2026-01-11T12:00:13+00:00","obs-2":"2026-01-11T12:00:20+00:00","obs-3":"2026-01-11T12:00:44+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.918,"edge-ai-1":0.63},"confidence":{"obs-1":0.83175,"obs-distractor":0.7,"obs-2":0.84175,"obs-3":0.9586},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9795857578083897,"event_time":"2026-01-11T12:00:30+00:00","arrival_time":"2026-01-11T12:00:44+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.48867367003172196,"normal":0.511326329968278},"reference_distribution":{"anomalous":0.020414242191610355,"normal":0.9795857578083897}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8045465,"event_time":"2026-01-11T12:00:10+00:00","arrival_time":"2026-01-11T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.19545349999999995,"normal":0.8045465}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-11T12:00:10+00:00","arrival_time":"2026-01-11T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8045465,"event_time":"2026-01-11T12:00:13+00:00","arrival_time":"2026-01-11T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19545349999999995,"normal":0.8045465},"reference_distribution":{"anomalous":0.19545349999999995,"normal":0.8045465}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-11T12:00:13+00:00","arrival_time":"2026-01-11T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.511326329968278,"event_time":"2026-01-11T12:00:20+00:00","arrival_time":"2026-01-11T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.19545349999999995,"normal":0.8045465},"reference_distribution":{"anomalous":0.48867367003172196,"normal":0.511326329968278}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-010-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-11T12:00:20+00:00","arrival_time":"2026-01-11T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9795857578083897,"event_time":"2026-01-11T12:00:30+00:00","arrival_time":"2026-01-11T12:00:44+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.48867367003172196,"normal":0.511326329968278},"reference_distribution":{"anomalous":0.020414242191610355,"normal":0.9795857578083897}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-11T12:00:30+00:00","arrival_time":"2026-01-11T12:00:44+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":10,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c8ec55ff4abad344e1224008ba8b6972236c697a0fee88e1f1597120f5a6bad2"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-011","name":"Evaluation v1.0 trajectory: contradiction_resolution case 011","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-011","label":"Distractor 011","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.831925,"modality":"semantic_status","timestamp":"2026-01-12T12:00:10Z","metadata":{"arrival_time":"2026-01-12T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-011","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.71,"modality":"semantic_status","timestamp":"2026-01-12T12:00:14Z","metadata":{"arrival_time":"2026-01-12T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.841925,"modality":"semantic_status","timestamp":"2026-01-12T12:00:20Z","metadata":{"arrival_time":"2026-01-12T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95846,"modality":"semantic_status","timestamp":"2026-01-12T12:00:30Z","metadata":{"arrival_time":"2026-01-12T12:00:45+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-01-12T12:00:10+00:00","obs-distractor":"2026-01-12T12:00:14+00:00","obs-2":"2026-01-12T12:00:20+00:00","obs-3":"2026-01-12T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-01-12T12:00:10+00:00","obs-distractor":"2026-01-12T12:00:14+00:00","obs-2":"2026-01-12T12:00:20+00:00","obs-3":"2026-01-12T12:00:45+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.926,"edge-ai-1":0.641},"confidence":{"obs-1":0.831925,"obs-distractor":0.71,"obs-2":0.841925,"obs-3":0.95846},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9498913705940548,"event_time":"2026-01-12T12:00:30+00:00","arrival_time":"2026-01-12T12:00:45+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5858811556709372,"normal":0.4141188443290627},"reference_distribution":{"anomalous":0.050108629405945286,"normal":0.9498913705940548}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7589015,"event_time":"2026-01-12T12:00:10+00:00","arrival_time":"2026-01-12T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2410985,"normal":0.7589015}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-12T12:00:10+00:00","arrival_time":"2026-01-12T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7589015,"event_time":"2026-01-12T12:00:14+00:00","arrival_time":"2026-01-12T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2410985,"normal":0.7589015},"reference_distribution":{"anomalous":0.2410985,"normal":0.7589015}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-12T12:00:14+00:00","arrival_time":"2026-01-12T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5858811556709372,"event_time":"2026-01-12T12:00:20+00:00","arrival_time":"2026-01-12T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2410985,"normal":0.7589015},"reference_distribution":{"anomalous":0.5858811556709372,"normal":0.4141188443290627}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-011-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-12T12:00:20+00:00","arrival_time":"2026-01-12T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9498913705940548,"event_time":"2026-01-12T12:00:30+00:00","arrival_time":"2026-01-12T12:00:45+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5858811556709372,"normal":0.4141188443290627},"reference_distribution":{"anomalous":0.050108629405945286,"normal":0.9498913705940548}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-12T12:00:30+00:00","arrival_time":"2026-01-12T12:00:45+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":11,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"a4412b189ae609e29322e6a602bbbcf1cd1ee847bb73b1fb96a56f343f909478"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-012","name":"Evaluation v1.0 trajectory: contradiction_resolution case 012","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-012","label":"Distractor 012","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8321,"modality":"semantic_status","timestamp":"2026-01-13T12:00:10Z","metadata":{"arrival_time":"2026-01-13T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-012","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.72,"modality":"semantic_status","timestamp":"2026-01-13T12:00:12Z","metadata":{"arrival_time":"2026-01-13T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8421,"modality":"semantic_status","timestamp":"2026-01-13T12:00:20Z","metadata":{"arrival_time":"2026-01-13T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95832,"modality":"semantic_status","timestamp":"2026-01-13T12:00:30Z","metadata":{"arrival_time":"2026-01-13T12:00:46+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-13T12:00:10+00:00","obs-distractor":"2026-01-13T12:00:12+00:00","obs-2":"2026-01-13T12:00:20+00:00","obs-3":"2026-01-13T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-01-13T12:00:10+00:00","obs-distractor":"2026-01-13T12:00:12+00:00","obs-2":"2026-01-13T12:00:20+00:00","obs-3":"2026-01-13T12:00:46+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.934,"edge-ai-1":0.652},"confidence":{"obs-1":0.8321,"obs-distractor":0.72,"obs-2":0.8421,"obs-3":0.95832},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9821653453175438,"event_time":"2026-01-13T12:00:30+00:00","arrival_time":"2026-01-13T12:00:46+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4394616379640675,"normal":0.5605383620359324},"reference_distribution":{"anomalous":0.01783465468245623,"normal":0.9821653453175438}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8101814,"event_time":"2026-01-13T12:00:10+00:00","arrival_time":"2026-01-13T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.18981859999999995,"normal":0.8101814}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-13T12:00:10+00:00","arrival_time":"2026-01-13T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8101814,"event_time":"2026-01-13T12:00:12+00:00","arrival_time":"2026-01-13T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.18981859999999995,"normal":0.8101814},"reference_distribution":{"anomalous":0.18981859999999995,"normal":0.8101814}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-13T12:00:12+00:00","arrival_time":"2026-01-13T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5605383620359324,"event_time":"2026-01-13T12:00:20+00:00","arrival_time":"2026-01-13T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.18981859999999995,"normal":0.8101814},"reference_distribution":{"anomalous":0.4394616379640675,"normal":0.5605383620359324}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-012-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-13T12:00:20+00:00","arrival_time":"2026-01-13T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9821653453175438,"event_time":"2026-01-13T12:00:30+00:00","arrival_time":"2026-01-13T12:00:46+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4394616379640675,"normal":0.5605383620359324},"reference_distribution":{"anomalous":0.01783465468245623,"normal":0.9821653453175438}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-13T12:00:30+00:00","arrival_time":"2026-01-13T12:00:46+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":12,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"b2afce274037851232ca2d23bec3227d589e90f1e8709519261e56e52dd75efa"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-013","name":"Evaluation v1.0 trajectory: contradiction_resolution case 013","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-013","label":"Distractor 013","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.832275,"modality":"semantic_status","timestamp":"2026-01-14T12:00:10Z","metadata":{"arrival_time":"2026-01-14T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.842275,"modality":"semantic_status","timestamp":"2026-01-14T12:00:20Z","metadata":{"arrival_time":"2026-01-14T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95818,"modality":"semantic_status","timestamp":"2026-01-14T12:00:30Z","metadata":{"arrival_time":"2026-01-14T12:00:47+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-013","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.73,"modality":"semantic_status","timestamp":"2026-01-14T12:00:13Z","metadata":{"arrival_time":"2026-01-14T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-14T12:00:10+00:00","obs-2":"2026-01-14T12:00:20+00:00","obs-3":"2026-01-14T12:00:30+00:00","obs-distractor":"2026-01-14T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-14T12:00:10+00:00","obs-2":"2026-01-14T12:00:20+00:00","obs-3":"2026-01-14T12:00:47+00:00","obs-distractor":"2026-01-14T12:00:13+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.942,"edge-ai-1":0.52},"confidence":{"obs-1":0.832275,"obs-2":0.842275,"obs-3":0.95818,"obs-distractor":0.73},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9545225772521925,"event_time":"2026-01-14T12:00:30+00:00","arrival_time":"2026-01-14T12:00:47+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5870287154546588,"normal":0.4129712845453411},"reference_distribution":{"anomalous":0.04547742274780749,"normal":0.9545225772521925}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.76515545,"event_time":"2026-01-14T12:00:10+00:00","arrival_time":"2026-01-14T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.23484455000000004,"normal":0.76515545}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-14T12:00:10+00:00","arrival_time":"2026-01-14T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.76515545,"event_time":"2026-01-14T12:00:13+00:00","arrival_time":"2026-01-14T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23484455000000004,"normal":0.76515545},"reference_distribution":{"anomalous":0.23484455000000004,"normal":0.76515545}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-14T12:00:13+00:00","arrival_time":"2026-01-14T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5870287154546588,"event_time":"2026-01-14T12:00:20+00:00","arrival_time":"2026-01-14T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23484455000000004,"normal":0.76515545},"reference_distribution":{"anomalous":0.5870287154546588,"normal":0.4129712845453411}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-013-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-14T12:00:20+00:00","arrival_time":"2026-01-14T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9545225772521925,"event_time":"2026-01-14T12:00:30+00:00","arrival_time":"2026-01-14T12:00:47+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5870287154546588,"normal":0.4129712845453411},"reference_distribution":{"anomalous":0.04547742274780749,"normal":0.9545225772521925}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-14T12:00:30+00:00","arrival_time":"2026-01-14T12:00:47+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":13,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"157667c8c9b41b99c8e5208a145b23f4793b24565f290aa0a54cb60a30c35c02"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-014","name":"Evaluation v1.0 trajectory: contradiction_resolution case 014","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-014","label":"Distractor 014","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.83245,"modality":"semantic_status","timestamp":"2026-01-15T12:00:10Z","metadata":{"arrival_time":"2026-01-15T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.84245,"modality":"semantic_status","timestamp":"2026-01-15T12:00:20Z","metadata":{"arrival_time":"2026-01-15T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95804,"modality":"semantic_status","timestamp":"2026-01-15T12:00:30Z","metadata":{"arrival_time":"2026-01-15T12:00:48+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-014","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.74,"modality":"semantic_status","timestamp":"2026-01-15T12:00:14Z","metadata":{"arrival_time":"2026-01-15T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-15T12:00:10+00:00","obs-2":"2026-01-15T12:00:20+00:00","obs-3":"2026-01-15T12:00:30+00:00","obs-distractor":"2026-01-15T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-15T12:00:10+00:00","obs-2":"2026-01-15T12:00:20+00:00","obs-3":"2026-01-15T12:00:48+00:00","obs-distractor":"2026-01-15T12:00:14+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.95,"edge-ai-1":0.531},"confidence":{"obs-1":0.83245,"obs-2":0.84245,"obs-3":0.95804,"obs-distractor":0.74},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9845832259949546,"event_time":"2026-01-15T12:00:30+00:00","arrival_time":"2026-01-15T12:00:48+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.43935804123641403,"normal":0.560641958763586},"reference_distribution":{"anomalous":0.015416774005045418,"normal":0.9845832259949546}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8158274999999999,"event_time":"2026-01-15T12:00:10+00:00","arrival_time":"2026-01-15T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.18417250000000007,"normal":0.8158274999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-15T12:00:10+00:00","arrival_time":"2026-01-15T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8158274999999999,"event_time":"2026-01-15T12:00:14+00:00","arrival_time":"2026-01-15T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.18417250000000007,"normal":0.8158274999999999},"reference_distribution":{"anomalous":0.18417250000000007,"normal":0.8158274999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-15T12:00:14+00:00","arrival_time":"2026-01-15T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.560641958763586,"event_time":"2026-01-15T12:00:20+00:00","arrival_time":"2026-01-15T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.18417250000000007,"normal":0.8158274999999999},"reference_distribution":{"anomalous":0.43935804123641403,"normal":0.560641958763586}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-014-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-15T12:00:20+00:00","arrival_time":"2026-01-15T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9845832259949546,"event_time":"2026-01-15T12:00:30+00:00","arrival_time":"2026-01-15T12:00:48+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.43935804123641403,"normal":0.560641958763586},"reference_distribution":{"anomalous":0.015416774005045418,"normal":0.9845832259949546}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-15T12:00:30+00:00","arrival_time":"2026-01-15T12:00:48+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":14,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"19c9b030d821ab9fcc90221df036efce01a770743851314d182da6f8c7e0445d"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-015","name":"Evaluation v1.0 trajectory: contradiction_resolution case 015","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-015","label":"Distractor 015","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.832625,"modality":"semantic_status","timestamp":"2026-01-16T12:00:10Z","metadata":{"arrival_time":"2026-01-16T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-015","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.75,"modality":"semantic_status","timestamp":"2026-01-16T12:00:12Z","metadata":{"arrival_time":"2026-01-16T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.842625,"modality":"semantic_status","timestamp":"2026-01-16T12:00:20Z","metadata":{"arrival_time":"2026-01-16T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9579,"modality":"semantic_status","timestamp":"2026-01-16T12:00:30Z","metadata":{"arrival_time":"2026-01-16T12:00:49+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-01-16T12:00:10+00:00","obs-distractor":"2026-01-16T12:00:12+00:00","obs-2":"2026-01-16T12:00:20+00:00","obs-3":"2026-01-16T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-01-16T12:00:10+00:00","obs-distractor":"2026-01-16T12:00:12+00:00","obs-2":"2026-01-16T12:00:20+00:00","obs-3":"2026-01-16T12:00:49+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.958,"edge-ai-1":0.542},"confidence":{"obs-1":0.832625,"obs-distractor":0.75,"obs-2":0.842625,"obs-3":0.9579},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9589067298481541,"event_time":"2026-01-16T12:00:30+00:00","arrival_time":"2026-01-16T12:00:49+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5882679707857339,"normal":0.4117320292142661},"reference_distribution":{"anomalous":0.04109327015184585,"normal":0.9589067298481541}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7714219999999999,"event_time":"2026-01-16T12:00:10+00:00","arrival_time":"2026-01-16T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.22857800000000006,"normal":0.7714219999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-16T12:00:10+00:00","arrival_time":"2026-01-16T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7714219999999999,"event_time":"2026-01-16T12:00:12+00:00","arrival_time":"2026-01-16T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22857800000000006,"normal":0.7714219999999999},"reference_distribution":{"anomalous":0.22857800000000006,"normal":0.7714219999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-16T12:00:12+00:00","arrival_time":"2026-01-16T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5882679707857339,"event_time":"2026-01-16T12:00:20+00:00","arrival_time":"2026-01-16T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22857800000000006,"normal":0.7714219999999999},"reference_distribution":{"anomalous":0.5882679707857339,"normal":0.4117320292142661}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-015-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-16T12:00:20+00:00","arrival_time":"2026-01-16T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9589067298481541,"event_time":"2026-01-16T12:00:30+00:00","arrival_time":"2026-01-16T12:00:49+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5882679707857339,"normal":0.4117320292142661},"reference_distribution":{"anomalous":0.04109327015184585,"normal":0.9589067298481541}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-16T12:00:30+00:00","arrival_time":"2026-01-16T12:00:49+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":15,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"246af86e576a4e612c53afe8c273ee79fc7f125d7cb98cfb6d9832c78de0bc70"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-016","name":"Evaluation v1.0 trajectory: contradiction_resolution case 016","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-016","label":"Distractor 016","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8328,"modality":"semantic_status","timestamp":"2026-01-17T12:00:10Z","metadata":{"arrival_time":"2026-01-17T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-016","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.76,"modality":"semantic_status","timestamp":"2026-01-17T12:00:13Z","metadata":{"arrival_time":"2026-01-17T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8428,"modality":"semantic_status","timestamp":"2026-01-17T12:00:20Z","metadata":{"arrival_time":"2026-01-17T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95776,"modality":"semantic_status","timestamp":"2026-01-17T12:00:30Z","metadata":{"arrival_time":"2026-01-17T12:00:50+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-17T12:00:10+00:00","obs-distractor":"2026-01-17T12:00:13+00:00","obs-2":"2026-01-17T12:00:20+00:00","obs-3":"2026-01-17T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-01-17T12:00:10+00:00","obs-distractor":"2026-01-17T12:00:13+00:00","obs-2":"2026-01-17T12:00:20+00:00","obs-3":"2026-01-17T12:00:50+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.966,"edge-ai-1":0.553},"confidence":{"obs-1":0.8328,"obs-distractor":0.76,"obs-2":0.8428,"obs-3":0.95776},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.986843531571146,"event_time":"2026-01-17T12:00:30+00:00","arrival_time":"2026-01-17T12:00:50+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4392214842261991,"normal":0.5607785157738009},"reference_distribution":{"anomalous":0.01315646842885399,"normal":0.986843531571146}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8214847999999999,"event_time":"2026-01-17T12:00:10+00:00","arrival_time":"2026-01-17T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1785152000000001,"normal":0.8214847999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-17T12:00:10+00:00","arrival_time":"2026-01-17T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8214847999999999,"event_time":"2026-01-17T12:00:13+00:00","arrival_time":"2026-01-17T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1785152000000001,"normal":0.8214847999999999},"reference_distribution":{"anomalous":0.1785152000000001,"normal":0.8214847999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-17T12:00:13+00:00","arrival_time":"2026-01-17T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5607785157738009,"event_time":"2026-01-17T12:00:20+00:00","arrival_time":"2026-01-17T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1785152000000001,"normal":0.8214847999999999},"reference_distribution":{"anomalous":0.4392214842261991,"normal":0.5607785157738009}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-016-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-17T12:00:20+00:00","arrival_time":"2026-01-17T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.986843531571146,"event_time":"2026-01-17T12:00:30+00:00","arrival_time":"2026-01-17T12:00:50+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4392214842261991,"normal":0.5607785157738009},"reference_distribution":{"anomalous":0.01315646842885399,"normal":0.986843531571146}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-17T12:00:30+00:00","arrival_time":"2026-01-17T12:00:50+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":16,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"4a3a859338e3e717e3072551a83f77f587f4530ab72d76744ecc7c0691dfa86d"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-017","name":"Evaluation v1.0 trajectory: contradiction_resolution case 017","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-017","label":"Distractor 017","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.832975,"modality":"semantic_status","timestamp":"2026-01-18T12:00:10Z","metadata":{"arrival_time":"2026-01-18T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-017","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.77,"modality":"semantic_status","timestamp":"2026-01-18T12:00:14Z","metadata":{"arrival_time":"2026-01-18T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.842975,"modality":"semantic_status","timestamp":"2026-01-18T12:00:20Z","metadata":{"arrival_time":"2026-01-18T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95762,"modality":"semantic_status","timestamp":"2026-01-18T12:00:30Z","metadata":{"arrival_time":"2026-01-18T12:00:34+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-01-18T12:00:10+00:00","obs-distractor":"2026-01-18T12:00:14+00:00","obs-2":"2026-01-18T12:00:20+00:00","obs-3":"2026-01-18T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-01-18T12:00:10+00:00","obs-distractor":"2026-01-18T12:00:14+00:00","obs-2":"2026-01-18T12:00:20+00:00","obs-3":"2026-01-18T12:00:34+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.974,"edge-ai-1":0.564},"confidence":{"obs-1":0.832975,"obs-distractor":0.77,"obs-2":0.842975,"obs-3":0.95762},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.963049199149847,"event_time":"2026-01-18T12:00:30+00:00","arrival_time":"2026-01-18T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5896073467577237,"normal":0.4103926532422763},"reference_distribution":{"anomalous":0.036950800850153016,"normal":0.963049199149847}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.77770115,"event_time":"2026-01-18T12:00:10+00:00","arrival_time":"2026-01-18T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.22229885000000005,"normal":0.77770115}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-18T12:00:10+00:00","arrival_time":"2026-01-18T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.77770115,"event_time":"2026-01-18T12:00:14+00:00","arrival_time":"2026-01-18T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22229885000000005,"normal":0.77770115},"reference_distribution":{"anomalous":0.22229885000000005,"normal":0.77770115}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-18T12:00:14+00:00","arrival_time":"2026-01-18T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5896073467577237,"event_time":"2026-01-18T12:00:20+00:00","arrival_time":"2026-01-18T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22229885000000005,"normal":0.77770115},"reference_distribution":{"anomalous":0.5896073467577237,"normal":0.4103926532422763}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-017-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-18T12:00:20+00:00","arrival_time":"2026-01-18T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.963049199149847,"event_time":"2026-01-18T12:00:30+00:00","arrival_time":"2026-01-18T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5896073467577237,"normal":0.4103926532422763},"reference_distribution":{"anomalous":0.036950800850153016,"normal":0.963049199149847}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-18T12:00:30+00:00","arrival_time":"2026-01-18T12:00:34+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":17,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"42d5032f5dea076259475241cfbcc279fc7aa11c77d602046270d52bed98dcaf"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-018","name":"Evaluation v1.0 trajectory: contradiction_resolution case 018","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-018","label":"Distractor 018","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.83315,"modality":"semantic_status","timestamp":"2026-01-19T12:00:10Z","metadata":{"arrival_time":"2026-01-19T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.84315,"modality":"semantic_status","timestamp":"2026-01-19T12:00:20Z","metadata":{"arrival_time":"2026-01-19T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95748,"modality":"semantic_status","timestamp":"2026-01-19T12:00:30Z","metadata":{"arrival_time":"2026-01-19T12:00:35+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-018","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.78,"modality":"semantic_status","timestamp":"2026-01-19T12:00:12Z","metadata":{"arrival_time":"2026-01-19T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-19T12:00:10+00:00","obs-2":"2026-01-19T12:00:20+00:00","obs-3":"2026-01-19T12:00:30+00:00","obs-distractor":"2026-01-19T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-19T12:00:10+00:00","obs-2":"2026-01-19T12:00:20+00:00","obs-3":"2026-01-19T12:00:35+00:00","obs-distractor":"2026-01-19T12:00:12+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.91,"edge-ai-1":0.575},"confidence":{"obs-1":0.83315,"obs-2":0.84315,"obs-3":0.95748,"obs-distractor":0.78},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9781058273048426,"event_time":"2026-01-19T12:00:30+00:00","arrival_time":"2026-01-19T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4786030000346962,"normal":0.5213969999653038},"reference_distribution":{"anomalous":0.021894172695157317,"normal":0.9781058273048426}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8031664999999999,"event_time":"2026-01-19T12:00:10+00:00","arrival_time":"2026-01-19T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1968335000000001,"normal":0.8031664999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-19T12:00:10+00:00","arrival_time":"2026-01-19T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8031664999999999,"event_time":"2026-01-19T12:00:12+00:00","arrival_time":"2026-01-19T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1968335000000001,"normal":0.8031664999999999},"reference_distribution":{"anomalous":0.1968335000000001,"normal":0.8031664999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-19T12:00:12+00:00","arrival_time":"2026-01-19T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5213969999653038,"event_time":"2026-01-19T12:00:20+00:00","arrival_time":"2026-01-19T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1968335000000001,"normal":0.8031664999999999},"reference_distribution":{"anomalous":0.4786030000346962,"normal":0.5213969999653038}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-018-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-19T12:00:20+00:00","arrival_time":"2026-01-19T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9781058273048426,"event_time":"2026-01-19T12:00:30+00:00","arrival_time":"2026-01-19T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4786030000346962,"normal":0.5213969999653038},"reference_distribution":{"anomalous":0.021894172695157317,"normal":0.9781058273048426}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-19T12:00:30+00:00","arrival_time":"2026-01-19T12:00:35+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":18,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"610473e10653fe627368e2bb08a4e4a1c0f99634f60120b17f3852a35b92b42d"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-019","name":"Evaluation v1.0 trajectory: contradiction_resolution case 019","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-019","label":"Distractor 019","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.833325,"modality":"semantic_status","timestamp":"2026-01-20T12:00:10Z","metadata":{"arrival_time":"2026-01-20T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.843325,"modality":"semantic_status","timestamp":"2026-01-20T12:00:20Z","metadata":{"arrival_time":"2026-01-20T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95734,"modality":"semantic_status","timestamp":"2026-01-20T12:00:30Z","metadata":{"arrival_time":"2026-01-20T12:00:36+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-019","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.79,"modality":"semantic_status","timestamp":"2026-01-20T12:00:13Z","metadata":{"arrival_time":"2026-01-20T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-20T12:00:10+00:00","obs-2":"2026-01-20T12:00:20+00:00","obs-3":"2026-01-20T12:00:30+00:00","obs-distractor":"2026-01-20T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-20T12:00:10+00:00","obs-2":"2026-01-20T12:00:20+00:00","obs-3":"2026-01-20T12:00:36+00:00","obs-distractor":"2026-01-20T12:00:13+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.918,"edge-ai-1":0.586},"confidence":{"obs-1":0.833325,"obs-2":0.843325,"obs-3":0.95734,"obs-distractor":0.79},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9669554945204829,"event_time":"2026-01-20T12:00:30+00:00","arrival_time":"2026-01-20T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5485681518789927,"normal":0.45143184812100734},"reference_distribution":{"anomalous":0.03304450547951706,"normal":0.9669554945204829}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7839929,"event_time":"2026-01-20T12:00:10+00:00","arrival_time":"2026-01-20T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2160071,"normal":0.7839929}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-20T12:00:10+00:00","arrival_time":"2026-01-20T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7839929,"event_time":"2026-01-20T12:00:13+00:00","arrival_time":"2026-01-20T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2160071,"normal":0.7839929},"reference_distribution":{"anomalous":0.2160071,"normal":0.7839929}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-20T12:00:13+00:00","arrival_time":"2026-01-20T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5485681518789927,"event_time":"2026-01-20T12:00:20+00:00","arrival_time":"2026-01-20T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2160071,"normal":0.7839929},"reference_distribution":{"anomalous":0.5485681518789927,"normal":0.45143184812100734}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-019-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-20T12:00:20+00:00","arrival_time":"2026-01-20T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9669554945204829,"event_time":"2026-01-20T12:00:30+00:00","arrival_time":"2026-01-20T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5485681518789927,"normal":0.45143184812100734},"reference_distribution":{"anomalous":0.03304450547951706,"normal":0.9669554945204829}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-20T12:00:30+00:00","arrival_time":"2026-01-20T12:00:36+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":19,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"f2b3285e8b34160c32689fb0ac9c5c79d442ff018a7f9d060681d73b669be315"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-020","name":"Evaluation v1.0 trajectory: contradiction_resolution case 020","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-020","label":"Distractor 020","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8335,"modality":"semantic_status","timestamp":"2026-01-21T12:00:10Z","metadata":{"arrival_time":"2026-01-21T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8435,"modality":"semantic_status","timestamp":"2026-01-21T12:00:20Z","metadata":{"arrival_time":"2026-01-21T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9572,"modality":"semantic_status","timestamp":"2026-01-21T12:00:30Z","metadata":{"arrival_time":"2026-01-21T12:00:37+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-020","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-01-21T12:00:14Z","metadata":{"arrival_time":"2026-01-21T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-21T12:00:10+00:00","obs-2":"2026-01-21T12:00:20+00:00","obs-3":"2026-01-21T12:00:30+00:00","obs-distractor":"2026-01-21T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-21T12:00:10+00:00","obs-2":"2026-01-21T12:00:20+00:00","obs-3":"2026-01-21T12:00:37+00:00","obs-distractor":"2026-01-21T12:00:14+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.926,"edge-ai-1":0.597},"confidence":{"obs-1":0.8335,"obs-2":0.8435,"obs-3":0.9572,"obs-distractor":0.6},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9807606215384247,"event_time":"2026-01-21T12:00:30+00:00","arrival_time":"2026-01-21T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4794102494655097,"normal":0.5205897505344903},"reference_distribution":{"anomalous":0.01923937846157534,"normal":0.9807606215384247}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.808821,"event_time":"2026-01-21T12:00:10+00:00","arrival_time":"2026-01-21T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.191179,"normal":0.808821}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-21T12:00:10+00:00","arrival_time":"2026-01-21T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.808821,"event_time":"2026-01-21T12:00:14+00:00","arrival_time":"2026-01-21T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.191179,"normal":0.808821},"reference_distribution":{"anomalous":0.191179,"normal":0.808821}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-21T12:00:14+00:00","arrival_time":"2026-01-21T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5205897505344903,"event_time":"2026-01-21T12:00:20+00:00","arrival_time":"2026-01-21T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.191179,"normal":0.808821},"reference_distribution":{"anomalous":0.4794102494655097,"normal":0.5205897505344903}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-020-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-21T12:00:20+00:00","arrival_time":"2026-01-21T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9807606215384247,"event_time":"2026-01-21T12:00:30+00:00","arrival_time":"2026-01-21T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4794102494655097,"normal":0.5205897505344903},"reference_distribution":{"anomalous":0.01923937846157534,"normal":0.9807606215384247}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-21T12:00:30+00:00","arrival_time":"2026-01-21T12:00:37+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":20,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c188790ce730096f53ba899bc969b5917ff5e508f612e6f7ef471db7685a2626"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-021","name":"Evaluation v1.0 trajectory: contradiction_resolution case 021","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-021","label":"Distractor 021","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.833675,"modality":"semantic_status","timestamp":"2026-01-22T12:00:10Z","metadata":{"arrival_time":"2026-01-22T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.843675,"modality":"semantic_status","timestamp":"2026-01-22T12:00:20Z","metadata":{"arrival_time":"2026-01-22T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95706,"modality":"semantic_status","timestamp":"2026-01-22T12:00:30Z","metadata":{"arrival_time":"2026-01-22T12:00:38+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-021","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-01-22T12:00:12Z","metadata":{"arrival_time":"2026-01-22T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-22T12:00:10+00:00","obs-2":"2026-01-22T12:00:20+00:00","obs-3":"2026-01-22T12:00:30+00:00","obs-distractor":"2026-01-22T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-22T12:00:10+00:00","obs-2":"2026-01-22T12:00:20+00:00","obs-3":"2026-01-22T12:00:38+00:00","obs-distractor":"2026-01-22T12:00:12+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.934,"edge-ai-1":0.608},"confidence":{"obs-1":0.833675,"obs-2":0.843675,"obs-3":0.95706,"obs-distractor":0.61},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9706312405698444,"event_time":"2026-01-22T12:00:30+00:00","arrival_time":"2026-01-22T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5489348159643596,"normal":0.45106518403564044},"reference_distribution":{"anomalous":0.02936875943015565,"normal":0.9706312405698444}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7902972500000001,"event_time":"2026-01-22T12:00:10+00:00","arrival_time":"2026-01-22T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.20970274999999994,"normal":0.7902972500000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-22T12:00:10+00:00","arrival_time":"2026-01-22T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7902972500000001,"event_time":"2026-01-22T12:00:12+00:00","arrival_time":"2026-01-22T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20970274999999994,"normal":0.7902972500000001},"reference_distribution":{"anomalous":0.20970274999999994,"normal":0.7902972500000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-22T12:00:12+00:00","arrival_time":"2026-01-22T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5489348159643596,"event_time":"2026-01-22T12:00:20+00:00","arrival_time":"2026-01-22T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20970274999999994,"normal":0.7902972500000001},"reference_distribution":{"anomalous":0.5489348159643596,"normal":0.45106518403564044}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-021-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-22T12:00:20+00:00","arrival_time":"2026-01-22T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9706312405698444,"event_time":"2026-01-22T12:00:30+00:00","arrival_time":"2026-01-22T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5489348159643596,"normal":0.45106518403564044},"reference_distribution":{"anomalous":0.02936875943015565,"normal":0.9706312405698444}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-22T12:00:30+00:00","arrival_time":"2026-01-22T12:00:38+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":21,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"1dc5f58c60d1c9c0ed93f1ab7985324e1e4ff28a2f96ce149653311d4901ea39"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-022","name":"Evaluation v1.0 trajectory: contradiction_resolution case 022","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-022","label":"Distractor 022","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.83385,"modality":"semantic_status","timestamp":"2026-01-23T12:00:10Z","metadata":{"arrival_time":"2026-01-23T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-022","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-01-23T12:00:13Z","metadata":{"arrival_time":"2026-01-23T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.84385,"modality":"semantic_status","timestamp":"2026-01-23T12:00:20Z","metadata":{"arrival_time":"2026-01-23T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95692,"modality":"semantic_status","timestamp":"2026-01-23T12:00:30Z","metadata":{"arrival_time":"2026-01-23T12:00:39+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-23T12:00:10+00:00","obs-distractor":"2026-01-23T12:00:13+00:00","obs-2":"2026-01-23T12:00:20+00:00","obs-3":"2026-01-23T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-01-23T12:00:10+00:00","obs-distractor":"2026-01-23T12:00:13+00:00","obs-2":"2026-01-23T12:00:20+00:00","obs-3":"2026-01-23T12:00:39+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.942,"edge-ai-1":0.619},"confidence":{"obs-1":0.83385,"obs-distractor":0.62,"obs-2":0.84385,"obs-3":0.95692},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9832517174824138,"event_time":"2026-01-23T12:00:30+00:00","arrival_time":"2026-01-23T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.43014992510553507,"normal":0.5698500748944649},"reference_distribution":{"anomalous":0.01674828251758624,"normal":0.9832517174824138}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8144867,"event_time":"2026-01-23T12:00:10+00:00","arrival_time":"2026-01-23T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1855133,"normal":0.8144867}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-23T12:00:10+00:00","arrival_time":"2026-01-23T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8144867,"event_time":"2026-01-23T12:00:13+00:00","arrival_time":"2026-01-23T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1855133,"normal":0.8144867},"reference_distribution":{"anomalous":0.1855133,"normal":0.8144867}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-23T12:00:13+00:00","arrival_time":"2026-01-23T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5698500748944649,"event_time":"2026-01-23T12:00:20+00:00","arrival_time":"2026-01-23T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1855133,"normal":0.8144867},"reference_distribution":{"anomalous":0.43014992510553507,"normal":0.5698500748944649}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-022-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-23T12:00:20+00:00","arrival_time":"2026-01-23T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9832517174824138,"event_time":"2026-01-23T12:00:30+00:00","arrival_time":"2026-01-23T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.43014992510553507,"normal":0.5698500748944649},"reference_distribution":{"anomalous":0.01674828251758624,"normal":0.9832517174824138}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-23T12:00:30+00:00","arrival_time":"2026-01-23T12:00:39+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":22,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"a37cec87460cc3ed47d7756d859e7c978ff184b209d144e300864c341dd2036d"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-023","name":"Evaluation v1.0 trajectory: contradiction_resolution case 023","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-023","label":"Distractor 023","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.834025,"modality":"semantic_status","timestamp":"2026-01-24T12:00:10Z","metadata":{"arrival_time":"2026-01-24T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-023","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-01-24T12:00:14Z","metadata":{"arrival_time":"2026-01-24T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.844025,"modality":"semantic_status","timestamp":"2026-01-24T12:00:20Z","metadata":{"arrival_time":"2026-01-24T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95678,"modality":"semantic_status","timestamp":"2026-01-24T12:00:30Z","metadata":{"arrival_time":"2026-01-24T12:00:40+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-01-24T12:00:10+00:00","obs-distractor":"2026-01-24T12:00:14+00:00","obs-2":"2026-01-24T12:00:20+00:00","obs-3":"2026-01-24T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-01-24T12:00:10+00:00","obs-distractor":"2026-01-24T12:00:14+00:00","obs-2":"2026-01-24T12:00:20+00:00","obs-3":"2026-01-24T12:00:40+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.95,"edge-ai-1":0.63},"confidence":{"obs-1":0.834025,"obs-distractor":0.63,"obs-2":0.844025,"obs-3":0.95678},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9521581124386824,"event_time":"2026-01-24T12:00:30+00:00","arrival_time":"2026-01-24T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5965386957513491,"normal":0.40346130424865084},"reference_distribution":{"anomalous":0.047841887561317596,"normal":0.9521581124386824}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.763545725,"event_time":"2026-01-24T12:00:10+00:00","arrival_time":"2026-01-24T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.23645427500000005,"normal":0.763545725}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-24T12:00:10+00:00","arrival_time":"2026-01-24T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.763545725,"event_time":"2026-01-24T12:00:14+00:00","arrival_time":"2026-01-24T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23645427500000005,"normal":0.763545725},"reference_distribution":{"anomalous":0.23645427500000005,"normal":0.763545725}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-24T12:00:14+00:00","arrival_time":"2026-01-24T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5965386957513491,"event_time":"2026-01-24T12:00:20+00:00","arrival_time":"2026-01-24T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23645427500000005,"normal":0.763545725},"reference_distribution":{"anomalous":0.5965386957513491,"normal":0.40346130424865084}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-023-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-24T12:00:20+00:00","arrival_time":"2026-01-24T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9521581124386824,"event_time":"2026-01-24T12:00:30+00:00","arrival_time":"2026-01-24T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5965386957513491,"normal":0.40346130424865084},"reference_distribution":{"anomalous":0.047841887561317596,"normal":0.9521581124386824}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-24T12:00:30+00:00","arrival_time":"2026-01-24T12:00:40+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":23,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"02ab14913ba8ca321f5461ce3b2b4cbf92005619e12b5ed1d569b270294231a6"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-024","name":"Evaluation v1.0 trajectory: contradiction_resolution case 024","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-024","label":"Distractor 024","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8342,"modality":"semantic_status","timestamp":"2026-01-25T12:00:10Z","metadata":{"arrival_time":"2026-01-25T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8442,"modality":"semantic_status","timestamp":"2026-01-25T12:00:20Z","metadata":{"arrival_time":"2026-01-25T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95664,"modality":"semantic_status","timestamp":"2026-01-25T12:00:30Z","metadata":{"arrival_time":"2026-01-25T12:00:41+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-024","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-01-25T12:00:12Z","metadata":{"arrival_time":"2026-01-25T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-25T12:00:10+00:00","obs-2":"2026-01-25T12:00:20+00:00","obs-3":"2026-01-25T12:00:30+00:00","obs-distractor":"2026-01-25T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-25T12:00:10+00:00","obs-2":"2026-01-25T12:00:20+00:00","obs-3":"2026-01-25T12:00:41+00:00","obs-distractor":"2026-01-25T12:00:12+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.958,"edge-ai-1":0.641},"confidence":{"obs-1":0.8342,"obs-2":0.8442,"obs-3":0.95664,"obs-distractor":0.64},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9855832535895247,"event_time":"2026-01-25T12:00:30+00:00","arrival_time":"2026-01-25T12:00:41+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.42982235374423283,"normal":0.5701776462557672},"reference_distribution":{"anomalous":0.01441674641047534,"normal":0.9855832535895247}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8201636000000001,"event_time":"2026-01-25T12:00:10+00:00","arrival_time":"2026-01-25T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1798363999999999,"normal":0.8201636000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-25T12:00:10+00:00","arrival_time":"2026-01-25T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8201636000000001,"event_time":"2026-01-25T12:00:12+00:00","arrival_time":"2026-01-25T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1798363999999999,"normal":0.8201636000000001},"reference_distribution":{"anomalous":0.1798363999999999,"normal":0.8201636000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-25T12:00:12+00:00","arrival_time":"2026-01-25T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5701776462557672,"event_time":"2026-01-25T12:00:20+00:00","arrival_time":"2026-01-25T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1798363999999999,"normal":0.8201636000000001},"reference_distribution":{"anomalous":0.42982235374423283,"normal":0.5701776462557672}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-024-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-25T12:00:20+00:00","arrival_time":"2026-01-25T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9855832535895247,"event_time":"2026-01-25T12:00:30+00:00","arrival_time":"2026-01-25T12:00:41+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.42982235374423283,"normal":0.5701776462557672},"reference_distribution":{"anomalous":0.01441674641047534,"normal":0.9855832535895247}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-25T12:00:30+00:00","arrival_time":"2026-01-25T12:00:41+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":24,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"7e6fbdc0eccdcd648b48106bde5c44594ca57a68d4d776bb02aa4a22efee3be0"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-025","name":"Evaluation v1.0 trajectory: contradiction_resolution case 025","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-025","label":"Distractor 025","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.834375,"modality":"semantic_status","timestamp":"2026-01-26T12:00:10Z","metadata":{"arrival_time":"2026-01-26T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.844375,"modality":"semantic_status","timestamp":"2026-01-26T12:00:20Z","metadata":{"arrival_time":"2026-01-26T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9565,"modality":"semantic_status","timestamp":"2026-01-26T12:00:30Z","metadata":{"arrival_time":"2026-01-26T12:00:42+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-025","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-01-26T12:00:13Z","metadata":{"arrival_time":"2026-01-26T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-26T12:00:10+00:00","obs-2":"2026-01-26T12:00:20+00:00","obs-3":"2026-01-26T12:00:30+00:00","obs-distractor":"2026-01-26T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-26T12:00:10+00:00","obs-2":"2026-01-26T12:00:20+00:00","obs-3":"2026-01-26T12:00:42+00:00","obs-distractor":"2026-01-26T12:00:13+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.966,"edge-ai-1":0.652},"confidence":{"obs-1":0.834375,"obs-2":0.844375,"obs-3":0.9565,"obs-distractor":0.65},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9566552522718593,"event_time":"2026-01-26T12:00:30+00:00","arrival_time":"2026-01-26T12:00:42+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5980222138454232,"normal":0.4019777861545768},"reference_distribution":{"anomalous":0.04334474772814058,"normal":0.9566552522718593}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7698406250000001,"event_time":"2026-01-26T12:00:10+00:00","arrival_time":"2026-01-26T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.23015937499999994,"normal":0.7698406250000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-26T12:00:10+00:00","arrival_time":"2026-01-26T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7698406250000001,"event_time":"2026-01-26T12:00:13+00:00","arrival_time":"2026-01-26T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23015937499999994,"normal":0.7698406250000001},"reference_distribution":{"anomalous":0.23015937499999994,"normal":0.7698406250000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-26T12:00:13+00:00","arrival_time":"2026-01-26T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5980222138454232,"event_time":"2026-01-26T12:00:20+00:00","arrival_time":"2026-01-26T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23015937499999994,"normal":0.7698406250000001},"reference_distribution":{"anomalous":0.5980222138454232,"normal":0.4019777861545768}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-025-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-26T12:00:20+00:00","arrival_time":"2026-01-26T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9566552522718593,"event_time":"2026-01-26T12:00:30+00:00","arrival_time":"2026-01-26T12:00:42+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5980222138454232,"normal":0.4019777861545768},"reference_distribution":{"anomalous":0.04334474772814058,"normal":0.9566552522718593}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-26T12:00:30+00:00","arrival_time":"2026-01-26T12:00:42+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":25,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"b1a5c07ada08c1011b95a771db4501e1a12b298673e97088bf679026d03dd8d7"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-026","name":"Evaluation v1.0 trajectory: contradiction_resolution case 026","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-026","label":"Distractor 026","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.83455,"modality":"semantic_status","timestamp":"2026-01-27T12:00:10Z","metadata":{"arrival_time":"2026-01-27T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-026","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-01-27T12:00:14Z","metadata":{"arrival_time":"2026-01-27T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.84455,"modality":"semantic_status","timestamp":"2026-01-27T12:00:20Z","metadata":{"arrival_time":"2026-01-27T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95636,"modality":"semantic_status","timestamp":"2026-01-27T12:00:30Z","metadata":{"arrival_time":"2026-01-27T12:00:43+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-27T12:00:10+00:00","obs-distractor":"2026-01-27T12:00:14+00:00","obs-2":"2026-01-27T12:00:20+00:00","obs-3":"2026-01-27T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-01-27T12:00:10+00:00","obs-distractor":"2026-01-27T12:00:14+00:00","obs-2":"2026-01-27T12:00:20+00:00","obs-3":"2026-01-27T12:00:43+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.974,"edge-ai-1":0.52},"confidence":{"obs-1":0.83455,"obs-distractor":0.66,"obs-2":0.84455,"obs-3":0.95636},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.987759370393921,"event_time":"2026-01-27T12:00:30+00:00","arrival_time":"2026-01-27T12:00:43+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.42944620538404754,"normal":0.5705537946159525},"reference_distribution":{"anomalous":0.01224062960607899,"normal":0.987759370393921}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8258517000000001,"event_time":"2026-01-27T12:00:10+00:00","arrival_time":"2026-01-27T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.17414829999999992,"normal":0.8258517000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-27T12:00:10+00:00","arrival_time":"2026-01-27T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8258517000000001,"event_time":"2026-01-27T12:00:14+00:00","arrival_time":"2026-01-27T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.17414829999999992,"normal":0.8258517000000001},"reference_distribution":{"anomalous":0.17414829999999992,"normal":0.8258517000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-27T12:00:14+00:00","arrival_time":"2026-01-27T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5705537946159525,"event_time":"2026-01-27T12:00:20+00:00","arrival_time":"2026-01-27T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.17414829999999992,"normal":0.8258517000000001},"reference_distribution":{"anomalous":0.42944620538404754,"normal":0.5705537946159525}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-026-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-27T12:00:20+00:00","arrival_time":"2026-01-27T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.987759370393921,"event_time":"2026-01-27T12:00:30+00:00","arrival_time":"2026-01-27T12:00:43+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.42944620538404754,"normal":0.5705537946159525},"reference_distribution":{"anomalous":0.01224062960607899,"normal":0.987759370393921}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-27T12:00:30+00:00","arrival_time":"2026-01-27T12:00:43+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":26,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"57ff7426a742b606202295bba2375a3e9e3fdf0839c2c51e1bdc1ec74908a0ce"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-027","name":"Evaluation v1.0 trajectory: contradiction_resolution case 027","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-027","label":"Distractor 027","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.834725,"modality":"semantic_status","timestamp":"2026-01-28T12:00:10Z","metadata":{"arrival_time":"2026-01-28T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-027","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-01-28T12:00:12Z","metadata":{"arrival_time":"2026-01-28T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.844725,"modality":"semantic_status","timestamp":"2026-01-28T12:00:20Z","metadata":{"arrival_time":"2026-01-28T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95622,"modality":"semantic_status","timestamp":"2026-01-28T12:00:30Z","metadata":{"arrival_time":"2026-01-28T12:00:44+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-01-28T12:00:10+00:00","obs-distractor":"2026-01-28T12:00:12+00:00","obs-2":"2026-01-28T12:00:20+00:00","obs-3":"2026-01-28T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-01-28T12:00:10+00:00","obs-distractor":"2026-01-28T12:00:12+00:00","obs-2":"2026-01-28T12:00:20+00:00","obs-3":"2026-01-28T12:00:44+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.91,"edge-ai-1":0.531},"confidence":{"obs-1":0.834725,"obs-distractor":0.67,"obs-2":0.844725,"obs-3":0.95622},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9609079730975347,"event_time":"2026-01-28T12:00:30+00:00","arrival_time":"2026-01-28T12:00:44+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5574632319912741,"normal":0.4425367680087258},"reference_distribution":{"anomalous":0.03909202690246522,"normal":0.9609079730975347}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.776148125,"event_time":"2026-01-28T12:00:10+00:00","arrival_time":"2026-01-28T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.22385187500000003,"normal":0.776148125}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-28T12:00:10+00:00","arrival_time":"2026-01-28T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.776148125,"event_time":"2026-01-28T12:00:12+00:00","arrival_time":"2026-01-28T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22385187500000003,"normal":0.776148125},"reference_distribution":{"anomalous":0.22385187500000003,"normal":0.776148125}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-28T12:00:12+00:00","arrival_time":"2026-01-28T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5574632319912741,"event_time":"2026-01-28T12:00:20+00:00","arrival_time":"2026-01-28T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22385187500000003,"normal":0.776148125},"reference_distribution":{"anomalous":0.5574632319912741,"normal":0.4425367680087258}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-027-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-28T12:00:20+00:00","arrival_time":"2026-01-28T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9609079730975347,"event_time":"2026-01-28T12:00:30+00:00","arrival_time":"2026-01-28T12:00:44+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5574632319912741,"normal":0.4425367680087258},"reference_distribution":{"anomalous":0.03909202690246522,"normal":0.9609079730975347}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-28T12:00:30+00:00","arrival_time":"2026-01-28T12:00:44+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":27,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"538bf4ef49229f2fe2af5c11c4a1ae7594dbbd0c247e0ecd1460a9d1792ca12b"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-028","name":"Evaluation v1.0 trajectory: contradiction_resolution case 028","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-028","label":"Distractor 028","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8349,"modality":"semantic_status","timestamp":"2026-01-29T12:00:10Z","metadata":{"arrival_time":"2026-01-29T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-028","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-01-29T12:00:13Z","metadata":{"arrival_time":"2026-01-29T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8449,"modality":"semantic_status","timestamp":"2026-01-29T12:00:20Z","metadata":{"arrival_time":"2026-01-29T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95608,"modality":"semantic_status","timestamp":"2026-01-29T12:00:30Z","metadata":{"arrival_time":"2026-01-29T12:00:45+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-29T12:00:10+00:00","obs-distractor":"2026-01-29T12:00:13+00:00","obs-2":"2026-01-29T12:00:20+00:00","obs-3":"2026-01-29T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-01-29T12:00:10+00:00","obs-distractor":"2026-01-29T12:00:13+00:00","obs-2":"2026-01-29T12:00:20+00:00","obs-3":"2026-01-29T12:00:45+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.918,"edge-ai-1":0.542},"confidence":{"obs-1":0.8349,"obs-distractor":0.68,"obs-2":0.8449,"obs-3":0.95608},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9793265428955021,"event_time":"2026-01-29T12:00:30+00:00","arrival_time":"2026-01-29T12:00:45+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4693754483679015,"normal":0.5306245516320985},"reference_distribution":{"anomalous":0.020673457104497802,"normal":0.9793265428955021}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8074382,"event_time":"2026-01-29T12:00:10+00:00","arrival_time":"2026-01-29T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1925618,"normal":0.8074382}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-29T12:00:10+00:00","arrival_time":"2026-01-29T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8074382,"event_time":"2026-01-29T12:00:13+00:00","arrival_time":"2026-01-29T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1925618,"normal":0.8074382},"reference_distribution":{"anomalous":0.1925618,"normal":0.8074382}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-29T12:00:13+00:00","arrival_time":"2026-01-29T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5306245516320985,"event_time":"2026-01-29T12:00:20+00:00","arrival_time":"2026-01-29T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1925618,"normal":0.8074382},"reference_distribution":{"anomalous":0.4693754483679015,"normal":0.5306245516320985}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-028-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-29T12:00:20+00:00","arrival_time":"2026-01-29T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9793265428955021,"event_time":"2026-01-29T12:00:30+00:00","arrival_time":"2026-01-29T12:00:45+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4693754483679015,"normal":0.5306245516320985},"reference_distribution":{"anomalous":0.020673457104497802,"normal":0.9793265428955021}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-29T12:00:30+00:00","arrival_time":"2026-01-29T12:00:45+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":28,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"8ad844748d085b52b8286705b19aa788df6a0eb653124992f315566ec1280989"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-029","name":"Evaluation v1.0 trajectory: contradiction_resolution case 029","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-029","label":"Distractor 029","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.835075,"modality":"semantic_status","timestamp":"2026-01-30T12:00:10Z","metadata":{"arrival_time":"2026-01-30T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.845075,"modality":"semantic_status","timestamp":"2026-01-30T12:00:20Z","metadata":{"arrival_time":"2026-01-30T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95594,"modality":"semantic_status","timestamp":"2026-01-30T12:00:30Z","metadata":{"arrival_time":"2026-01-30T12:00:46+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-029","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-01-30T12:00:14Z","metadata":{"arrival_time":"2026-01-30T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-30T12:00:10+00:00","obs-2":"2026-01-30T12:00:20+00:00","obs-3":"2026-01-30T12:00:30+00:00","obs-distractor":"2026-01-30T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-30T12:00:10+00:00","obs-2":"2026-01-30T12:00:20+00:00","obs-3":"2026-01-30T12:00:46+00:00","obs-distractor":"2026-01-30T12:00:14+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.926,"edge-ai-1":0.553},"confidence":{"obs-1":0.835075,"obs-2":0.845075,"obs-3":0.95594,"obs-distractor":0.69},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9649217407844541,"event_time":"2026-01-30T12:00:30+00:00","arrival_time":"2026-01-30T12:00:46+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5580179744482904,"normal":0.4419820255517096},"reference_distribution":{"anomalous":0.035078259215545964,"normal":0.9649217407844541}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.782468225,"event_time":"2026-01-30T12:00:10+00:00","arrival_time":"2026-01-30T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.21753177499999998,"normal":0.782468225}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-30T12:00:10+00:00","arrival_time":"2026-01-30T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.782468225,"event_time":"2026-01-30T12:00:14+00:00","arrival_time":"2026-01-30T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.21753177499999998,"normal":0.782468225},"reference_distribution":{"anomalous":0.21753177499999998,"normal":0.782468225}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-30T12:00:14+00:00","arrival_time":"2026-01-30T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5580179744482904,"event_time":"2026-01-30T12:00:20+00:00","arrival_time":"2026-01-30T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.21753177499999998,"normal":0.782468225},"reference_distribution":{"anomalous":0.5580179744482904,"normal":0.4419820255517096}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-029-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-30T12:00:20+00:00","arrival_time":"2026-01-30T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9649217407844541,"event_time":"2026-01-30T12:00:30+00:00","arrival_time":"2026-01-30T12:00:46+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5580179744482904,"normal":0.4419820255517096},"reference_distribution":{"anomalous":0.035078259215545964,"normal":0.9649217407844541}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-30T12:00:30+00:00","arrival_time":"2026-01-30T12:00:46+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":29,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"365a28ce43f133a3ca854d2a090c42bd50e19ce3091f5e2bdca3713d7c7f01de"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-030","name":"Evaluation v1.0 trajectory: contradiction_resolution case 030","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-030","label":"Distractor 030","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.83525,"modality":"semantic_status","timestamp":"2026-01-31T12:00:10Z","metadata":{"arrival_time":"2026-01-31T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.84525,"modality":"semantic_status","timestamp":"2026-01-31T12:00:20Z","metadata":{"arrival_time":"2026-01-31T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9558,"modality":"semantic_status","timestamp":"2026-01-31T12:00:30Z","metadata":{"arrival_time":"2026-01-31T12:00:47+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-030","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.7,"modality":"semantic_status","timestamp":"2026-01-31T12:00:12Z","metadata":{"arrival_time":"2026-01-31T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-31T12:00:10+00:00","obs-2":"2026-01-31T12:00:20+00:00","obs-3":"2026-01-31T12:00:30+00:00","obs-distractor":"2026-01-31T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-31T12:00:10+00:00","obs-2":"2026-01-31T12:00:20+00:00","obs-3":"2026-01-31T12:00:47+00:00","obs-distractor":"2026-01-31T12:00:12+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.934,"edge-ai-1":0.564},"confidence":{"obs-1":0.83525,"obs-2":0.84525,"obs-3":0.9558,"obs-distractor":0.7},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9818919448463188,"event_time":"2026-01-31T12:00:30+00:00","arrival_time":"2026-01-31T12:00:47+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.46996319356753136,"normal":0.5300368064324686},"reference_distribution":{"anomalous":0.01810805515368114,"normal":0.9818919448463188}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8131235000000001,"event_time":"2026-01-31T12:00:10+00:00","arrival_time":"2026-01-31T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1868764999999999,"normal":0.8131235000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-31T12:00:10+00:00","arrival_time":"2026-01-31T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8131235000000001,"event_time":"2026-01-31T12:00:12+00:00","arrival_time":"2026-01-31T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1868764999999999,"normal":0.8131235000000001},"reference_distribution":{"anomalous":0.1868764999999999,"normal":0.8131235000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-31T12:00:12+00:00","arrival_time":"2026-01-31T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5300368064324686,"event_time":"2026-01-31T12:00:20+00:00","arrival_time":"2026-01-31T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1868764999999999,"normal":0.8131235000000001},"reference_distribution":{"anomalous":0.46996319356753136,"normal":0.5300368064324686}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-030-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-31T12:00:20+00:00","arrival_time":"2026-01-31T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9818919448463188,"event_time":"2026-01-31T12:00:30+00:00","arrival_time":"2026-01-31T12:00:47+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.46996319356753136,"normal":0.5300368064324686},"reference_distribution":{"anomalous":0.01810805515368114,"normal":0.9818919448463188}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-31T12:00:30+00:00","arrival_time":"2026-01-31T12:00:47+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":30,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"58e8560aa01a2c2f66e4d47533248b2c661632ab9eb031827fece43981066c03"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-031","name":"Evaluation v1.0 trajectory: contradiction_resolution case 031","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-031","label":"Distractor 031","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.835425,"modality":"semantic_status","timestamp":"2026-02-01T12:00:10Z","metadata":{"arrival_time":"2026-02-01T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.845425,"modality":"semantic_status","timestamp":"2026-02-01T12:00:20Z","metadata":{"arrival_time":"2026-02-01T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95566,"modality":"semantic_status","timestamp":"2026-02-01T12:00:30Z","metadata":{"arrival_time":"2026-02-01T12:00:48+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-031","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.71,"modality":"semantic_status","timestamp":"2026-02-01T12:00:13Z","metadata":{"arrival_time":"2026-02-01T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-01T12:00:10+00:00","obs-2":"2026-02-01T12:00:20+00:00","obs-3":"2026-02-01T12:00:30+00:00","obs-distractor":"2026-02-01T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-01T12:00:10+00:00","obs-2":"2026-02-01T12:00:20+00:00","obs-3":"2026-02-01T12:00:48+00:00","obs-distractor":"2026-02-01T12:00:13+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.942,"edge-ai-1":0.575},"confidence":{"obs-1":0.835425,"obs-2":0.845425,"obs-3":0.95566,"obs-distractor":0.71},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9687021469239671,"event_time":"2026-02-01T12:00:30+00:00","arrival_time":"2026-02-01T12:00:48+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5586267649008421,"normal":0.44137323509915793},"reference_distribution":{"anomalous":0.03129785307603301,"normal":0.9687021469239671}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.788800925,"event_time":"2026-02-01T12:00:10+00:00","arrival_time":"2026-02-01T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.21119907500000001,"normal":0.788800925}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-01T12:00:10+00:00","arrival_time":"2026-02-01T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.788800925,"event_time":"2026-02-01T12:00:13+00:00","arrival_time":"2026-02-01T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.21119907500000001,"normal":0.788800925},"reference_distribution":{"anomalous":0.21119907500000001,"normal":0.788800925}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-01T12:00:13+00:00","arrival_time":"2026-02-01T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5586267649008421,"event_time":"2026-02-01T12:00:20+00:00","arrival_time":"2026-02-01T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.21119907500000001,"normal":0.788800925},"reference_distribution":{"anomalous":0.5586267649008421,"normal":0.44137323509915793}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-031-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-01T12:00:20+00:00","arrival_time":"2026-02-01T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9687021469239671,"event_time":"2026-02-01T12:00:30+00:00","arrival_time":"2026-02-01T12:00:48+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5586267649008421,"normal":0.44137323509915793},"reference_distribution":{"anomalous":0.03129785307603301,"normal":0.9687021469239671}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-01T12:00:30+00:00","arrival_time":"2026-02-01T12:00:48+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":31,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"db4a37956f820ea083155e351c98d82337a4be8c07c4c2c48876b81236b8e735"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-032","name":"Evaluation v1.0 trajectory: contradiction_resolution case 032","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-032","label":"Distractor 032","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8356,"modality":"semantic_status","timestamp":"2026-02-02T12:00:10Z","metadata":{"arrival_time":"2026-02-02T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8456,"modality":"semantic_status","timestamp":"2026-02-02T12:00:20Z","metadata":{"arrival_time":"2026-02-02T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95552,"modality":"semantic_status","timestamp":"2026-02-02T12:00:30Z","metadata":{"arrival_time":"2026-02-02T12:00:49+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-032","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.72,"modality":"semantic_status","timestamp":"2026-02-02T12:00:14Z","metadata":{"arrival_time":"2026-02-02T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-02T12:00:10+00:00","obs-2":"2026-02-02T12:00:20+00:00","obs-3":"2026-02-02T12:00:30+00:00","obs-distractor":"2026-02-02T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-02T12:00:10+00:00","obs-2":"2026-02-02T12:00:20+00:00","obs-3":"2026-02-02T12:00:49+00:00","obs-distractor":"2026-02-02T12:00:14+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.95,"edge-ai-1":0.586},"confidence":{"obs-1":0.8356,"obs-2":0.8456,"obs-3":0.95552,"obs-distractor":0.72},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9842957929476368,"event_time":"2026-02-02T12:00:30+00:00","arrival_time":"2026-02-02T12:00:49+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4705656723014383,"normal":0.5294343276985617},"reference_distribution":{"anomalous":0.015704207052363073,"normal":0.9842957929476368}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.81882,"event_time":"2026-02-02T12:00:10+00:00","arrival_time":"2026-02-02T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.18118,"normal":0.81882}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-02T12:00:10+00:00","arrival_time":"2026-02-02T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.81882,"event_time":"2026-02-02T12:00:14+00:00","arrival_time":"2026-02-02T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.18118,"normal":0.81882},"reference_distribution":{"anomalous":0.18118,"normal":0.81882}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-02T12:00:14+00:00","arrival_time":"2026-02-02T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5294343276985617,"event_time":"2026-02-02T12:00:20+00:00","arrival_time":"2026-02-02T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.18118,"normal":0.81882},"reference_distribution":{"anomalous":0.4705656723014383,"normal":0.5294343276985617}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-032-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-02T12:00:20+00:00","arrival_time":"2026-02-02T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9842957929476368,"event_time":"2026-02-02T12:00:30+00:00","arrival_time":"2026-02-02T12:00:49+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4705656723014383,"normal":0.5294343276985617},"reference_distribution":{"anomalous":0.015704207052363073,"normal":0.9842957929476368}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-02T12:00:30+00:00","arrival_time":"2026-02-02T12:00:49+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":32,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"87f8db912d069fce6a54f12668db55aa0a2e4c8f6ede035b02f5080b6abdb20d"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-033","name":"Evaluation v1.0 trajectory: contradiction_resolution case 033","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-033","label":"Distractor 033","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.835775,"modality":"semantic_status","timestamp":"2026-02-03T12:00:10Z","metadata":{"arrival_time":"2026-02-03T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.845775,"modality":"semantic_status","timestamp":"2026-02-03T12:00:20Z","metadata":{"arrival_time":"2026-02-03T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95538,"modality":"semantic_status","timestamp":"2026-02-03T12:00:30Z","metadata":{"arrival_time":"2026-02-03T12:00:50+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-033","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.73,"modality":"semantic_status","timestamp":"2026-02-03T12:00:12Z","metadata":{"arrival_time":"2026-02-03T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-03T12:00:10+00:00","obs-2":"2026-02-03T12:00:20+00:00","obs-3":"2026-02-03T12:00:30+00:00","obs-distractor":"2026-02-03T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-03T12:00:10+00:00","obs-2":"2026-02-03T12:00:20+00:00","obs-3":"2026-02-03T12:00:50+00:00","obs-distractor":"2026-02-03T12:00:12+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.958,"edge-ai-1":0.597},"confidence":{"obs-1":0.835775,"obs-2":0.845775,"obs-3":0.95538,"obs-distractor":0.73},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9497458921349511,"event_time":"2026-02-03T12:00:30+00:00","arrival_time":"2026-02-03T12:00:50+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6062032379502429,"normal":0.3937967620497571},"reference_distribution":{"anomalous":0.0502541078650488,"normal":0.9497458921349511}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7619045,"event_time":"2026-02-03T12:00:10+00:00","arrival_time":"2026-02-03T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.23809550000000002,"normal":0.7619045}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-03T12:00:10+00:00","arrival_time":"2026-02-03T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7619045,"event_time":"2026-02-03T12:00:12+00:00","arrival_time":"2026-02-03T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23809550000000002,"normal":0.7619045},"reference_distribution":{"anomalous":0.23809550000000002,"normal":0.7619045}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-03T12:00:12+00:00","arrival_time":"2026-02-03T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6062032379502429,"event_time":"2026-02-03T12:00:20+00:00","arrival_time":"2026-02-03T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23809550000000002,"normal":0.7619045},"reference_distribution":{"anomalous":0.6062032379502429,"normal":0.3937967620497571}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-033-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-03T12:00:20+00:00","arrival_time":"2026-02-03T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9497458921349511,"event_time":"2026-02-03T12:00:30+00:00","arrival_time":"2026-02-03T12:00:50+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6062032379502429,"normal":0.3937967620497571},"reference_distribution":{"anomalous":0.0502541078650488,"normal":0.9497458921349511}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-03T12:00:30+00:00","arrival_time":"2026-02-03T12:00:50+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":33,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"194d1139d7fdeab31d77831a5dadd4a79fcd662c1cb3bc9e543cb4fb9ee07d6d"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-034","name":"Evaluation v1.0 trajectory: contradiction_resolution case 034","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-034","label":"Distractor 034","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.83595,"modality":"semantic_status","timestamp":"2026-02-04T12:00:10Z","metadata":{"arrival_time":"2026-02-04T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-034","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.74,"modality":"semantic_status","timestamp":"2026-02-04T12:00:13Z","metadata":{"arrival_time":"2026-02-04T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.84595,"modality":"semantic_status","timestamp":"2026-02-04T12:00:20Z","metadata":{"arrival_time":"2026-02-04T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95524,"modality":"semantic_status","timestamp":"2026-02-04T12:00:30Z","metadata":{"arrival_time":"2026-02-04T12:00:34+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-04T12:00:10+00:00","obs-distractor":"2026-02-04T12:00:13+00:00","obs-2":"2026-02-04T12:00:20+00:00","obs-3":"2026-02-04T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-02-04T12:00:10+00:00","obs-distractor":"2026-02-04T12:00:13+00:00","obs-2":"2026-02-04T12:00:20+00:00","obs-3":"2026-02-04T12:00:34+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.966,"edge-ai-1":0.608},"confidence":{"obs-1":0.83595,"obs-distractor":0.74,"obs-2":0.84595,"obs-3":0.95524},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9865422364623806,"event_time":"2026-02-04T12:00:30+00:00","arrival_time":"2026-02-04T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.42012518695949735,"normal":0.5798748130405026},"reference_distribution":{"anomalous":0.013457763537619436,"normal":0.9865422364623806}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8245277,"event_time":"2026-02-04T12:00:10+00:00","arrival_time":"2026-02-04T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.17547230000000003,"normal":0.8245277}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-04T12:00:10+00:00","arrival_time":"2026-02-04T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8245277,"event_time":"2026-02-04T12:00:13+00:00","arrival_time":"2026-02-04T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.17547230000000003,"normal":0.8245277},"reference_distribution":{"anomalous":0.17547230000000003,"normal":0.8245277}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-04T12:00:13+00:00","arrival_time":"2026-02-04T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5798748130405026,"event_time":"2026-02-04T12:00:20+00:00","arrival_time":"2026-02-04T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.17547230000000003,"normal":0.8245277},"reference_distribution":{"anomalous":0.42012518695949735,"normal":0.5798748130405026}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-034-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-04T12:00:20+00:00","arrival_time":"2026-02-04T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9865422364623806,"event_time":"2026-02-04T12:00:30+00:00","arrival_time":"2026-02-04T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.42012518695949735,"normal":0.5798748130405026},"reference_distribution":{"anomalous":0.013457763537619436,"normal":0.9865422364623806}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-04T12:00:30+00:00","arrival_time":"2026-02-04T12:00:34+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":34,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c8977fad07f4584339824d9cbb8e5482652e8cbc7f3ec99b58a9cbdaa0242be2"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-035","name":"Evaluation v1.0 trajectory: contradiction_resolution case 035","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-035","label":"Distractor 035","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.836125,"modality":"semantic_status","timestamp":"2026-02-05T12:00:10Z","metadata":{"arrival_time":"2026-02-05T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.846125,"modality":"semantic_status","timestamp":"2026-02-05T12:00:20Z","metadata":{"arrival_time":"2026-02-05T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9551,"modality":"semantic_status","timestamp":"2026-02-05T12:00:30Z","metadata":{"arrival_time":"2026-02-05T12:00:35+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-035","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.75,"modality":"semantic_status","timestamp":"2026-02-05T12:00:14Z","metadata":{"arrival_time":"2026-02-05T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-05T12:00:10+00:00","obs-2":"2026-02-05T12:00:20+00:00","obs-3":"2026-02-05T12:00:30+00:00","obs-distractor":"2026-02-05T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-05T12:00:10+00:00","obs-2":"2026-02-05T12:00:20+00:00","obs-3":"2026-02-05T12:00:35+00:00","obs-distractor":"2026-02-05T12:00:14+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.974,"edge-ai-1":0.619},"confidence":{"obs-1":0.836125,"obs-2":0.846125,"obs-3":0.9551,"obs-distractor":0.75},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9543576166158887,"event_time":"2026-02-05T12:00:30+00:00","arrival_time":"2026-02-05T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6079408422524647,"normal":0.39205915774753525},"reference_distribution":{"anomalous":0.045642383384111224,"normal":0.9543576166158887}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7682277500000001,"event_time":"2026-02-05T12:00:10+00:00","arrival_time":"2026-02-05T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.2317722499999999,"normal":0.7682277500000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-05T12:00:10+00:00","arrival_time":"2026-02-05T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7682277500000001,"event_time":"2026-02-05T12:00:14+00:00","arrival_time":"2026-02-05T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2317722499999999,"normal":0.7682277500000001},"reference_distribution":{"anomalous":0.2317722499999999,"normal":0.7682277500000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-05T12:00:14+00:00","arrival_time":"2026-02-05T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6079408422524647,"event_time":"2026-02-05T12:00:20+00:00","arrival_time":"2026-02-05T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.2317722499999999,"normal":0.7682277500000001},"reference_distribution":{"anomalous":0.6079408422524647,"normal":0.39205915774753525}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-035-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-05T12:00:20+00:00","arrival_time":"2026-02-05T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9543576166158887,"event_time":"2026-02-05T12:00:30+00:00","arrival_time":"2026-02-05T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6079408422524647,"normal":0.39205915774753525},"reference_distribution":{"anomalous":0.045642383384111224,"normal":0.9543576166158887}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-05T12:00:30+00:00","arrival_time":"2026-02-05T12:00:35+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":35,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"894ebf01a92cf8c06b4a382df23ba25397895560bb56c4c44f0729e271a59250"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-036","name":"Evaluation v1.0 trajectory: contradiction_resolution case 036","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-036","label":"Distractor 036","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8363,"modality":"semantic_status","timestamp":"2026-02-06T12:00:10Z","metadata":{"arrival_time":"2026-02-06T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8463,"modality":"semantic_status","timestamp":"2026-02-06T12:00:20Z","metadata":{"arrival_time":"2026-02-06T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95496,"modality":"semantic_status","timestamp":"2026-02-06T12:00:30Z","metadata":{"arrival_time":"2026-02-06T12:00:36+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-036","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.76,"modality":"semantic_status","timestamp":"2026-02-06T12:00:12Z","metadata":{"arrival_time":"2026-02-06T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-06T12:00:10+00:00","obs-2":"2026-02-06T12:00:20+00:00","obs-3":"2026-02-06T12:00:30+00:00","obs-distractor":"2026-02-06T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-06T12:00:10+00:00","obs-2":"2026-02-06T12:00:20+00:00","obs-3":"2026-02-06T12:00:36+00:00","obs-distractor":"2026-02-06T12:00:12+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.91,"edge-ai-1":0.63},"confidence":{"obs-1":0.8363,"obs-2":0.8463,"obs-3":0.95496,"obs-distractor":0.76},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9778624325872134,"event_time":"2026-02-06T12:00:30+00:00","arrival_time":"2026-02-06T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.45961553690410584,"normal":0.5403844630958942},"reference_distribution":{"anomalous":0.02213756741278661,"normal":0.9778624325872134}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.806033,"event_time":"2026-02-06T12:00:10+00:00","arrival_time":"2026-02-06T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.193967,"normal":0.806033}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-06T12:00:10+00:00","arrival_time":"2026-02-06T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.806033,"event_time":"2026-02-06T12:00:12+00:00","arrival_time":"2026-02-06T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.193967,"normal":0.806033},"reference_distribution":{"anomalous":0.193967,"normal":0.806033}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-06T12:00:12+00:00","arrival_time":"2026-02-06T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5403844630958942,"event_time":"2026-02-06T12:00:20+00:00","arrival_time":"2026-02-06T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.193967,"normal":0.806033},"reference_distribution":{"anomalous":0.45961553690410584,"normal":0.5403844630958942}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-036-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-06T12:00:20+00:00","arrival_time":"2026-02-06T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9778624325872134,"event_time":"2026-02-06T12:00:30+00:00","arrival_time":"2026-02-06T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.45961553690410584,"normal":0.5403844630958942},"reference_distribution":{"anomalous":0.02213756741278661,"normal":0.9778624325872134}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-06T12:00:30+00:00","arrival_time":"2026-02-06T12:00:36+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":36,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"d61b7493edff3070a00d2d3bdb50cdc111b343ebfa05b902dfbcd38c11205d0d"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-037","name":"Evaluation v1.0 trajectory: contradiction_resolution case 037","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-037","label":"Distractor 037","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.836475,"modality":"semantic_status","timestamp":"2026-02-07T12:00:10Z","metadata":{"arrival_time":"2026-02-07T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-037","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.77,"modality":"semantic_status","timestamp":"2026-02-07T12:00:13Z","metadata":{"arrival_time":"2026-02-07T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.846475,"modality":"semantic_status","timestamp":"2026-02-07T12:00:20Z","metadata":{"arrival_time":"2026-02-07T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95482,"modality":"semantic_status","timestamp":"2026-02-07T12:00:30Z","metadata":{"arrival_time":"2026-02-07T12:00:37+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-02-07T12:00:10+00:00","obs-distractor":"2026-02-07T12:00:13+00:00","obs-2":"2026-02-07T12:00:20+00:00","obs-3":"2026-02-07T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-02-07T12:00:10+00:00","obs-distractor":"2026-02-07T12:00:13+00:00","obs-2":"2026-02-07T12:00:20+00:00","obs-3":"2026-02-07T12:00:37+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.918,"edge-ai-1":0.641},"confidence":{"obs-1":0.836475,"obs-distractor":0.77,"obs-2":0.846475,"obs-3":0.95482},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9587222012335034,"event_time":"2026-02-07T12:00:30+00:00","arrival_time":"2026-02-07T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5668533410250277,"normal":0.4331466589749723},"reference_distribution":{"anomalous":0.04127779876649663,"normal":0.9587222012335034}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7745636,"event_time":"2026-02-07T12:00:10+00:00","arrival_time":"2026-02-07T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.22543639999999998,"normal":0.7745636}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-07T12:00:10+00:00","arrival_time":"2026-02-07T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7745636,"event_time":"2026-02-07T12:00:13+00:00","arrival_time":"2026-02-07T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22543639999999998,"normal":0.7745636},"reference_distribution":{"anomalous":0.22543639999999998,"normal":0.7745636}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-07T12:00:13+00:00","arrival_time":"2026-02-07T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5668533410250277,"event_time":"2026-02-07T12:00:20+00:00","arrival_time":"2026-02-07T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22543639999999998,"normal":0.7745636},"reference_distribution":{"anomalous":0.5668533410250277,"normal":0.4331466589749723}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-037-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-07T12:00:20+00:00","arrival_time":"2026-02-07T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9587222012335034,"event_time":"2026-02-07T12:00:30+00:00","arrival_time":"2026-02-07T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5668533410250277,"normal":0.4331466589749723},"reference_distribution":{"anomalous":0.04127779876649663,"normal":0.9587222012335034}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-07T12:00:30+00:00","arrival_time":"2026-02-07T12:00:37+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":37,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"10cfd0efd05b2004bcb9f6ed4b1921c3034887900439418eec338d60c0571190"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-038","name":"Evaluation v1.0 trajectory: contradiction_resolution case 038","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-038","label":"Distractor 038","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.83665,"modality":"semantic_status","timestamp":"2026-02-08T12:00:10Z","metadata":{"arrival_time":"2026-02-08T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.84665,"modality":"semantic_status","timestamp":"2026-02-08T12:00:20Z","metadata":{"arrival_time":"2026-02-08T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95468,"modality":"semantic_status","timestamp":"2026-02-08T12:00:30Z","metadata":{"arrival_time":"2026-02-08T12:00:38+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-038","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.78,"modality":"semantic_status","timestamp":"2026-02-08T12:00:14Z","metadata":{"arrival_time":"2026-02-08T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-08T12:00:10+00:00","obs-2":"2026-02-08T12:00:20+00:00","obs-3":"2026-02-08T12:00:30+00:00","obs-distractor":"2026-02-08T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-08T12:00:10+00:00","obs-2":"2026-02-08T12:00:20+00:00","obs-3":"2026-02-08T12:00:38+00:00","obs-distractor":"2026-02-08T12:00:14+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.926,"edge-ai-1":0.652},"confidence":{"obs-1":0.83665,"obs-2":0.84665,"obs-3":0.95468,"obs-distractor":0.78},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.980503237780509,"event_time":"2026-02-08T12:00:30+00:00","arrival_time":"2026-02-08T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4599749910537474,"normal":0.5400250089462526},"reference_distribution":{"anomalous":0.019496762219491034,"normal":0.980503237780509}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8117379,"event_time":"2026-02-08T12:00:10+00:00","arrival_time":"2026-02-08T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1882621,"normal":0.8117379}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-08T12:00:10+00:00","arrival_time":"2026-02-08T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8117379,"event_time":"2026-02-08T12:00:14+00:00","arrival_time":"2026-02-08T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1882621,"normal":0.8117379},"reference_distribution":{"anomalous":0.1882621,"normal":0.8117379}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-08T12:00:14+00:00","arrival_time":"2026-02-08T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5400250089462526,"event_time":"2026-02-08T12:00:20+00:00","arrival_time":"2026-02-08T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1882621,"normal":0.8117379},"reference_distribution":{"anomalous":0.4599749910537474,"normal":0.5400250089462526}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-038-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-08T12:00:20+00:00","arrival_time":"2026-02-08T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.980503237780509,"event_time":"2026-02-08T12:00:30+00:00","arrival_time":"2026-02-08T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4599749910537474,"normal":0.5400250089462526},"reference_distribution":{"anomalous":0.019496762219491034,"normal":0.980503237780509}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-08T12:00:30+00:00","arrival_time":"2026-02-08T12:00:38+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":38,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"3b19958d461a6a6b50b432eeb5fd4dc31baadaad9412bd3c7145f3fda9252f07"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-039","name":"Evaluation v1.0 trajectory: contradiction_resolution case 039","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-039","label":"Distractor 039","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.836825,"modality":"semantic_status","timestamp":"2026-02-09T12:00:10Z","metadata":{"arrival_time":"2026-02-09T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.846825,"modality":"semantic_status","timestamp":"2026-02-09T12:00:20Z","metadata":{"arrival_time":"2026-02-09T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95454,"modality":"semantic_status","timestamp":"2026-02-09T12:00:30Z","metadata":{"arrival_time":"2026-02-09T12:00:39+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-039","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.79,"modality":"semantic_status","timestamp":"2026-02-09T12:00:12Z","metadata":{"arrival_time":"2026-02-09T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-09T12:00:10+00:00","obs-2":"2026-02-09T12:00:20+00:00","obs-3":"2026-02-09T12:00:30+00:00","obs-distractor":"2026-02-09T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-09T12:00:10+00:00","obs-2":"2026-02-09T12:00:20+00:00","obs-3":"2026-02-09T12:00:39+00:00","obs-distractor":"2026-02-09T12:00:12+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.934,"edge-ai-1":0.52},"confidence":{"obs-1":0.836825,"obs-2":0.846825,"obs-3":0.95454,"obs-distractor":0.79},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9628450630097255,"event_time":"2026-02-09T12:00:30+00:00","arrival_time":"2026-02-09T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5676442143624173,"normal":0.4323557856375827},"reference_distribution":{"anomalous":0.0371549369902746,"normal":0.9628450630097255}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.78091205,"event_time":"2026-02-09T12:00:10+00:00","arrival_time":"2026-02-09T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.21908795000000003,"normal":0.78091205}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-09T12:00:10+00:00","arrival_time":"2026-02-09T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.78091205,"event_time":"2026-02-09T12:00:12+00:00","arrival_time":"2026-02-09T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.21908795000000003,"normal":0.78091205},"reference_distribution":{"anomalous":0.21908795000000003,"normal":0.78091205}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-09T12:00:12+00:00","arrival_time":"2026-02-09T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5676442143624173,"event_time":"2026-02-09T12:00:20+00:00","arrival_time":"2026-02-09T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.21908795000000003,"normal":0.78091205},"reference_distribution":{"anomalous":0.5676442143624173,"normal":0.4323557856375827}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-039-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-09T12:00:20+00:00","arrival_time":"2026-02-09T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9628450630097255,"event_time":"2026-02-09T12:00:30+00:00","arrival_time":"2026-02-09T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5676442143624173,"normal":0.4323557856375827},"reference_distribution":{"anomalous":0.0371549369902746,"normal":0.9628450630097255}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-09T12:00:30+00:00","arrival_time":"2026-02-09T12:00:39+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":39,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"680dbdd64090738b8fea6688004af7c348c77c223de49b706817929d5694eb56"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-040","name":"Evaluation v1.0 trajectory: contradiction_resolution case 040","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-040","label":"Distractor 040","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.837,"modality":"semantic_status","timestamp":"2026-02-10T12:00:10Z","metadata":{"arrival_time":"2026-02-10T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-040","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-02-10T12:00:13Z","metadata":{"arrival_time":"2026-02-10T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.847,"modality":"semantic_status","timestamp":"2026-02-10T12:00:20Z","metadata":{"arrival_time":"2026-02-10T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9544,"modality":"semantic_status","timestamp":"2026-02-10T12:00:30Z","metadata":{"arrival_time":"2026-02-10T12:00:40+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-10T12:00:10+00:00","obs-distractor":"2026-02-10T12:00:13+00:00","obs-2":"2026-02-10T12:00:20+00:00","obs-3":"2026-02-10T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-02-10T12:00:10+00:00","obs-distractor":"2026-02-10T12:00:13+00:00","obs-2":"2026-02-10T12:00:20+00:00","obs-3":"2026-02-10T12:00:40+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.942,"edge-ai-1":0.531},"confidence":{"obs-1":0.837,"obs-distractor":0.6,"obs-2":0.847,"obs-3":0.9544},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9829804866690128,"event_time":"2026-02-10T12:00:30+00:00","arrival_time":"2026-02-10T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4603326472644709,"normal":0.5396673527355291},"reference_distribution":{"anomalous":0.01701951333098722,"normal":0.9829804866690128}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8174539999999999,"event_time":"2026-02-10T12:00:10+00:00","arrival_time":"2026-02-10T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1825460000000001,"normal":0.8174539999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-10T12:00:10+00:00","arrival_time":"2026-02-10T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8174539999999999,"event_time":"2026-02-10T12:00:13+00:00","arrival_time":"2026-02-10T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1825460000000001,"normal":0.8174539999999999},"reference_distribution":{"anomalous":0.1825460000000001,"normal":0.8174539999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-10T12:00:13+00:00","arrival_time":"2026-02-10T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5396673527355291,"event_time":"2026-02-10T12:00:20+00:00","arrival_time":"2026-02-10T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1825460000000001,"normal":0.8174539999999999},"reference_distribution":{"anomalous":0.4603326472644709,"normal":0.5396673527355291}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-040-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-10T12:00:20+00:00","arrival_time":"2026-02-10T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9829804866690128,"event_time":"2026-02-10T12:00:30+00:00","arrival_time":"2026-02-10T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4603326472644709,"normal":0.5396673527355291},"reference_distribution":{"anomalous":0.01701951333098722,"normal":0.9829804866690128}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-10T12:00:30+00:00","arrival_time":"2026-02-10T12:00:40+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":40,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"8c8b61b557e28b403cd7403a0495fc87c2c123466e3ae7883b8c91ca88db663b"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-041","name":"Evaluation v1.0 trajectory: contradiction_resolution case 041","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-041","label":"Distractor 041","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.837175,"modality":"semantic_status","timestamp":"2026-02-11T12:00:10Z","metadata":{"arrival_time":"2026-02-11T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.847175,"modality":"semantic_status","timestamp":"2026-02-11T12:00:20Z","metadata":{"arrival_time":"2026-02-11T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95426,"modality":"semantic_status","timestamp":"2026-02-11T12:00:30Z","metadata":{"arrival_time":"2026-02-11T12:00:41+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-041","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-02-11T12:00:14Z","metadata":{"arrival_time":"2026-02-11T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-11T12:00:10+00:00","obs-2":"2026-02-11T12:00:20+00:00","obs-3":"2026-02-11T12:00:30+00:00","obs-distractor":"2026-02-11T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-11T12:00:10+00:00","obs-2":"2026-02-11T12:00:20+00:00","obs-3":"2026-02-11T12:00:41+00:00","obs-distractor":"2026-02-11T12:00:14+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.95,"edge-ai-1":0.542},"confidence":{"obs-1":0.837175,"obs-2":0.847175,"obs-3":0.95426,"obs-distractor":0.61},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9667317555220183,"event_time":"2026-02-11T12:00:30+00:00","arrival_time":"2026-02-11T12:00:41+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5685063126446771,"normal":0.43149368735532284},"reference_distribution":{"anomalous":0.03326824447798161,"normal":0.9667317555220183}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7872731,"event_time":"2026-02-11T12:00:10+00:00","arrival_time":"2026-02-11T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.21272690000000005,"normal":0.7872731}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-11T12:00:10+00:00","arrival_time":"2026-02-11T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7872731,"event_time":"2026-02-11T12:00:14+00:00","arrival_time":"2026-02-11T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.21272690000000005,"normal":0.7872731},"reference_distribution":{"anomalous":0.21272690000000005,"normal":0.7872731}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-11T12:00:14+00:00","arrival_time":"2026-02-11T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5685063126446771,"event_time":"2026-02-11T12:00:20+00:00","arrival_time":"2026-02-11T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.21272690000000005,"normal":0.7872731},"reference_distribution":{"anomalous":0.5685063126446771,"normal":0.43149368735532284}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-041-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-11T12:00:20+00:00","arrival_time":"2026-02-11T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9667317555220183,"event_time":"2026-02-11T12:00:30+00:00","arrival_time":"2026-02-11T12:00:41+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5685063126446771,"normal":0.43149368735532284},"reference_distribution":{"anomalous":0.03326824447798161,"normal":0.9667317555220183}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-11T12:00:30+00:00","arrival_time":"2026-02-11T12:00:41+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":41,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"50861e582d9c3cc55b845ff7f86ab3474caf3f4ab4d9ff91913bc1213901ec8f"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-042","name":"Evaluation v1.0 trajectory: contradiction_resolution case 042","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-042","label":"Distractor 042","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.83735,"modality":"semantic_status","timestamp":"2026-02-12T12:00:10Z","metadata":{"arrival_time":"2026-02-12T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.84735,"modality":"semantic_status","timestamp":"2026-02-12T12:00:20Z","metadata":{"arrival_time":"2026-02-12T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95412,"modality":"semantic_status","timestamp":"2026-02-12T12:00:30Z","metadata":{"arrival_time":"2026-02-12T12:00:42+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-042","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-02-12T12:00:12Z","metadata":{"arrival_time":"2026-02-12T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-12T12:00:10+00:00","obs-2":"2026-02-12T12:00:20+00:00","obs-3":"2026-02-12T12:00:30+00:00","obs-distractor":"2026-02-12T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-12T12:00:10+00:00","obs-2":"2026-02-12T12:00:20+00:00","obs-3":"2026-02-12T12:00:42+00:00","obs-distractor":"2026-02-12T12:00:12+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.958,"edge-ai-1":0.553},"confidence":{"obs-1":0.83735,"obs-2":0.84735,"obs-3":0.95412,"obs-distractor":0.62},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9852983355613445,"event_time":"2026-02-12T12:00:30+00:00","arrival_time":"2026-02-12T12:00:42+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4606888349931615,"normal":0.5393111650068385},"reference_distribution":{"anomalous":0.01470166443865543,"normal":0.9852983355613445}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8231813,"event_time":"2026-02-12T12:00:10+00:00","arrival_time":"2026-02-12T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.1768187,"normal":0.8231813}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-12T12:00:10+00:00","arrival_time":"2026-02-12T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8231813,"event_time":"2026-02-12T12:00:12+00:00","arrival_time":"2026-02-12T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1768187,"normal":0.8231813},"reference_distribution":{"anomalous":0.1768187,"normal":0.8231813}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-12T12:00:12+00:00","arrival_time":"2026-02-12T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5393111650068385,"event_time":"2026-02-12T12:00:20+00:00","arrival_time":"2026-02-12T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.1768187,"normal":0.8231813},"reference_distribution":{"anomalous":0.4606888349931615,"normal":0.5393111650068385}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-042-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-12T12:00:20+00:00","arrival_time":"2026-02-12T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9852983355613445,"event_time":"2026-02-12T12:00:30+00:00","arrival_time":"2026-02-12T12:00:42+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4606888349931615,"normal":0.5393111650068385},"reference_distribution":{"anomalous":0.01470166443865543,"normal":0.9852983355613445}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-12T12:00:30+00:00","arrival_time":"2026-02-12T12:00:42+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":42,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"91feac0f9879f15329080ce2a9d042219094c01eacf1a09fcb5087dcc2e26382"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-043","name":"Evaluation v1.0 trajectory: contradiction_resolution case 043","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-043","label":"Distractor 043","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.837525,"modality":"semantic_status","timestamp":"2026-02-13T12:00:10Z","metadata":{"arrival_time":"2026-02-13T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.847525,"modality":"semantic_status","timestamp":"2026-02-13T12:00:20Z","metadata":{"arrival_time":"2026-02-13T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95398,"modality":"semantic_status","timestamp":"2026-02-13T12:00:30Z","metadata":{"arrival_time":"2026-02-13T12:00:43+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-043","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-02-13T12:00:13Z","metadata":{"arrival_time":"2026-02-13T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-13T12:00:10+00:00","obs-2":"2026-02-13T12:00:20+00:00","obs-3":"2026-02-13T12:00:30+00:00","obs-distractor":"2026-02-13T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-13T12:00:10+00:00","obs-2":"2026-02-13T12:00:20+00:00","obs-3":"2026-02-13T12:00:43+00:00","obs-distractor":"2026-02-13T12:00:13+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.966,"edge-ai-1":0.564},"confidence":{"obs-1":0.837525,"obs-2":0.847525,"obs-3":0.95398,"obs-distractor":0.63},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9703879454759962,"event_time":"2026-02-13T12:00:30+00:00","arrival_time":"2026-02-13T12:00:43+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5694465269705075,"normal":0.4305534730294925},"reference_distribution":{"anomalous":0.029612054524003825,"normal":0.9703879454759962}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.79364675,"event_time":"2026-02-13T12:00:10+00:00","arrival_time":"2026-02-13T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.20635325000000004,"normal":0.79364675}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-13T12:00:10+00:00","arrival_time":"2026-02-13T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.79364675,"event_time":"2026-02-13T12:00:13+00:00","arrival_time":"2026-02-13T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20635325000000004,"normal":0.79364675},"reference_distribution":{"anomalous":0.20635325000000004,"normal":0.79364675}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-13T12:00:13+00:00","arrival_time":"2026-02-13T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5694465269705075,"event_time":"2026-02-13T12:00:20+00:00","arrival_time":"2026-02-13T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.20635325000000004,"normal":0.79364675},"reference_distribution":{"anomalous":0.5694465269705075,"normal":0.4305534730294925}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-043-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-13T12:00:20+00:00","arrival_time":"2026-02-13T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9703879454759962,"event_time":"2026-02-13T12:00:30+00:00","arrival_time":"2026-02-13T12:00:43+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5694465269705075,"normal":0.4305534730294925},"reference_distribution":{"anomalous":0.029612054524003825,"normal":0.9703879454759962}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-13T12:00:30+00:00","arrival_time":"2026-02-13T12:00:43+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":43,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"a148ac48685b7e64af1c6e65f1087b6ed647c75dda0ffee2077132fdf1308dc9"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-044","name":"Evaluation v1.0 trajectory: contradiction_resolution case 044","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-044","label":"Distractor 044","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8377,"modality":"semantic_status","timestamp":"2026-02-14T12:00:10Z","metadata":{"arrival_time":"2026-02-14T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8477,"modality":"semantic_status","timestamp":"2026-02-14T12:00:20Z","metadata":{"arrival_time":"2026-02-14T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95384,"modality":"semantic_status","timestamp":"2026-02-14T12:00:30Z","metadata":{"arrival_time":"2026-02-14T12:00:44+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-044","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-02-14T12:00:14Z","metadata":{"arrival_time":"2026-02-14T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-14T12:00:10+00:00","obs-2":"2026-02-14T12:00:20+00:00","obs-3":"2026-02-14T12:00:30+00:00","obs-distractor":"2026-02-14T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-14T12:00:10+00:00","obs-2":"2026-02-14T12:00:20+00:00","obs-3":"2026-02-14T12:00:44+00:00","obs-distractor":"2026-02-14T12:00:14+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.974,"edge-ai-1":0.575},"confidence":{"obs-1":0.8377,"obs-2":0.8477,"obs-3":0.95384,"obs-distractor":0.64},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9874609416732122,"event_time":"2026-02-14T12:00:30+00:00","arrival_time":"2026-02-14T12:00:44+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4102680301697655,"normal":0.5897319698302346},"reference_distribution":{"anomalous":0.012539058326787804,"normal":0.9874609416732122}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8289198,"event_time":"2026-02-14T12:00:10+00:00","arrival_time":"2026-02-14T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.17108020000000002,"normal":0.8289198}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-14T12:00:10+00:00","arrival_time":"2026-02-14T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8289198,"event_time":"2026-02-14T12:00:14+00:00","arrival_time":"2026-02-14T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.17108020000000002,"normal":0.8289198},"reference_distribution":{"anomalous":0.17108020000000002,"normal":0.8289198}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-14T12:00:14+00:00","arrival_time":"2026-02-14T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5897319698302346,"event_time":"2026-02-14T12:00:20+00:00","arrival_time":"2026-02-14T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.17108020000000002,"normal":0.8289198},"reference_distribution":{"anomalous":0.4102680301697655,"normal":0.5897319698302346}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-044-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-14T12:00:20+00:00","arrival_time":"2026-02-14T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9874609416732122,"event_time":"2026-02-14T12:00:30+00:00","arrival_time":"2026-02-14T12:00:44+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4102680301697655,"normal":0.5897319698302346},"reference_distribution":{"anomalous":0.012539058326787804,"normal":0.9874609416732122}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-14T12:00:30+00:00","arrival_time":"2026-02-14T12:00:44+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":44,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"a7814afc1805a6919a7580b495f9ba7579b93fc181f20aecc1cead9bc0f4eff2"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-045","name":"Evaluation v1.0 trajectory: contradiction_resolution case 045","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-045","label":"Distractor 045","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.837875,"modality":"semantic_status","timestamp":"2026-02-15T12:00:10Z","metadata":{"arrival_time":"2026-02-15T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-045","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-02-15T12:00:12Z","metadata":{"arrival_time":"2026-02-15T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.847875,"modality":"semantic_status","timestamp":"2026-02-15T12:00:20Z","metadata":{"arrival_time":"2026-02-15T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9537,"modality":"semantic_status","timestamp":"2026-02-15T12:00:30Z","metadata":{"arrival_time":"2026-02-15T12:00:45+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-02-15T12:00:10+00:00","obs-distractor":"2026-02-15T12:00:12+00:00","obs-2":"2026-02-15T12:00:20+00:00","obs-3":"2026-02-15T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-02-15T12:00:10+00:00","obs-distractor":"2026-02-15T12:00:12+00:00","obs-2":"2026-02-15T12:00:20+00:00","obs-3":"2026-02-15T12:00:45+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.91,"edge-ai-1":0.586},"confidence":{"obs-1":0.837875,"obs-distractor":0.65,"obs-2":0.847875,"obs-3":0.9537},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9520127741528221,"event_time":"2026-02-15T12:00:30+00:00","arrival_time":"2026-02-15T12:00:45+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5754532744952777,"normal":0.4245467255047223},"reference_distribution":{"anomalous":0.04798722584717795,"normal":0.9520127741528221}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7665833750000001,"event_time":"2026-02-15T12:00:10+00:00","arrival_time":"2026-02-15T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.23341662499999993,"normal":0.7665833750000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-15T12:00:10+00:00","arrival_time":"2026-02-15T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7665833750000001,"event_time":"2026-02-15T12:00:12+00:00","arrival_time":"2026-02-15T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23341662499999993,"normal":0.7665833750000001},"reference_distribution":{"anomalous":0.23341662499999993,"normal":0.7665833750000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-15T12:00:12+00:00","arrival_time":"2026-02-15T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5754532744952777,"event_time":"2026-02-15T12:00:20+00:00","arrival_time":"2026-02-15T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.23341662499999993,"normal":0.7665833750000001},"reference_distribution":{"anomalous":0.5754532744952777,"normal":0.4245467255047223}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-045-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-15T12:00:20+00:00","arrival_time":"2026-02-15T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9520127741528221,"event_time":"2026-02-15T12:00:30+00:00","arrival_time":"2026-02-15T12:00:45+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5754532744952777,"normal":0.4245467255047223},"reference_distribution":{"anomalous":0.04798722584717795,"normal":0.9520127741528221}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-15T12:00:30+00:00","arrival_time":"2026-02-15T12:00:45+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":45,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"6c608b7bc3f0e7a30c78ec83f5edad460766398b69650b69075ae052b425a513"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-046","name":"Evaluation v1.0 trajectory: contradiction_resolution case 046","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-046","label":"Distractor 046","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.83805,"modality":"semantic_status","timestamp":"2026-02-16T12:00:10Z","metadata":{"arrival_time":"2026-02-16T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-046","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-02-16T12:00:13Z","metadata":{"arrival_time":"2026-02-16T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.84805,"modality":"semantic_status","timestamp":"2026-02-16T12:00:20Z","metadata":{"arrival_time":"2026-02-16T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95356,"modality":"semantic_status","timestamp":"2026-02-16T12:00:30Z","metadata":{"arrival_time":"2026-02-16T12:00:46+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-16T12:00:10+00:00","obs-distractor":"2026-02-16T12:00:13+00:00","obs-2":"2026-02-16T12:00:20+00:00","obs-3":"2026-02-16T12:00:30+00:00"},"arrival_times":{"obs-1":"2026-02-16T12:00:10+00:00","obs-distractor":"2026-02-16T12:00:13+00:00","obs-2":"2026-02-16T12:00:20+00:00","obs-3":"2026-02-16T12:00:46+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.918,"edge-ai-1":0.597},"confidence":{"obs-1":0.83805,"obs-distractor":0.66,"obs-2":0.84805,"obs-3":0.95356},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1,"obs-3":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9790849221224281,"event_time":"2026-02-16T12:00:30+00:00","arrival_time":"2026-02-16T12:00:46+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.45026792481313904,"normal":0.549732075186861},"reference_distribution":{"anomalous":0.020915077877571853,"normal":0.9790849221224281}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8103298999999999,"event_time":"2026-02-16T12:00:10+00:00","arrival_time":"2026-02-16T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.18967010000000006,"normal":0.8103298999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-16T12:00:10+00:00","arrival_time":"2026-02-16T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8103298999999999,"event_time":"2026-02-16T12:00:13+00:00","arrival_time":"2026-02-16T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.18967010000000006,"normal":0.8103298999999999},"reference_distribution":{"anomalous":0.18967010000000006,"normal":0.8103298999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-16T12:00:13+00:00","arrival_time":"2026-02-16T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.549732075186861,"event_time":"2026-02-16T12:00:20+00:00","arrival_time":"2026-02-16T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.18967010000000006,"normal":0.8103298999999999},"reference_distribution":{"anomalous":0.45026792481313904,"normal":0.549732075186861}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-046-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-16T12:00:20+00:00","arrival_time":"2026-02-16T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9790849221224281,"event_time":"2026-02-16T12:00:30+00:00","arrival_time":"2026-02-16T12:00:46+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.45026792481313904,"normal":0.549732075186861},"reference_distribution":{"anomalous":0.020915077877571853,"normal":0.9790849221224281}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-16T12:00:30+00:00","arrival_time":"2026-02-16T12:00:46+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":46,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"220a776581bc2b2c207501ab33618ec30a5e38605bedfc441ece0d3e454ffbd3"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-047","name":"Evaluation v1.0 trajectory: contradiction_resolution case 047","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-047","label":"Distractor 047","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.838225,"modality":"semantic_status","timestamp":"2026-02-17T12:00:10Z","metadata":{"arrival_time":"2026-02-17T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.848225,"modality":"semantic_status","timestamp":"2026-02-17T12:00:20Z","metadata":{"arrival_time":"2026-02-17T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95342,"modality":"semantic_status","timestamp":"2026-02-17T12:00:30Z","metadata":{"arrival_time":"2026-02-17T12:00:47+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-047","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-02-17T12:00:14Z","metadata":{"arrival_time":"2026-02-17T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-17T12:00:10+00:00","obs-2":"2026-02-17T12:00:20+00:00","obs-3":"2026-02-17T12:00:30+00:00","obs-distractor":"2026-02-17T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-17T12:00:10+00:00","obs-2":"2026-02-17T12:00:20+00:00","obs-3":"2026-02-17T12:00:47+00:00","obs-distractor":"2026-02-17T12:00:14+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.926,"edge-ai-1":0.608},"confidence":{"obs-1":0.838225,"obs-2":0.848225,"obs-3":0.95342,"obs-distractor":0.67},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9564908321162585,"event_time":"2026-02-17T12:00:30+00:00","arrival_time":"2026-02-17T12:00:47+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5764088822837888,"normal":0.42359111771621116},"reference_distribution":{"anomalous":0.04350916788374148,"normal":0.9564908321162585}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.772947575,"event_time":"2026-02-17T12:00:10+00:00","arrival_time":"2026-02-17T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.227052425,"normal":0.772947575}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-17T12:00:10+00:00","arrival_time":"2026-02-17T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.772947575,"event_time":"2026-02-17T12:00:14+00:00","arrival_time":"2026-02-17T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.227052425,"normal":0.772947575},"reference_distribution":{"anomalous":0.227052425,"normal":0.772947575}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-17T12:00:14+00:00","arrival_time":"2026-02-17T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5764088822837888,"event_time":"2026-02-17T12:00:20+00:00","arrival_time":"2026-02-17T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.227052425,"normal":0.772947575},"reference_distribution":{"anomalous":0.5764088822837888,"normal":0.42359111771621116}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-047-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-17T12:00:20+00:00","arrival_time":"2026-02-17T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9564908321162585,"event_time":"2026-02-17T12:00:30+00:00","arrival_time":"2026-02-17T12:00:47+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5764088822837888,"normal":0.42359111771621116},"reference_distribution":{"anomalous":0.04350916788374148,"normal":0.9564908321162585}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-17T12:00:30+00:00","arrival_time":"2026-02-17T12:00:47+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":47,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"63b0c4def2335df5c2edf18d13b71f94b15ee3af3db88c9019064e8d2720a6fc"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-048","name":"Evaluation v1.0 trajectory: contradiction_resolution case 048","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-048","label":"Distractor 048","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8384,"modality":"semantic_status","timestamp":"2026-02-18T12:00:10Z","metadata":{"arrival_time":"2026-02-18T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8484,"modality":"semantic_status","timestamp":"2026-02-18T12:00:20Z","metadata":{"arrival_time":"2026-02-18T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95328,"modality":"semantic_status","timestamp":"2026-02-18T12:00:30Z","metadata":{"arrival_time":"2026-02-18T12:00:48+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-048","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-02-18T12:00:12Z","metadata":{"arrival_time":"2026-02-18T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-18T12:00:10+00:00","obs-2":"2026-02-18T12:00:20+00:00","obs-3":"2026-02-18T12:00:30+00:00","obs-distractor":"2026-02-18T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-18T12:00:10+00:00","obs-2":"2026-02-18T12:00:20+00:00","obs-3":"2026-02-18T12:00:48+00:00","obs-distractor":"2026-02-18T12:00:12+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.934,"edge-ai-1":0.619},"confidence":{"obs-1":0.8384,"obs-2":0.8484,"obs-3":0.95328,"obs-distractor":0.68},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9816366675185271,"event_time":"2026-02-18T12:00:30+00:00","arrival_time":"2026-02-18T12:00:48+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4504022371471764,"normal":0.5495977628528236},"reference_distribution":{"anomalous":0.018363332481472976,"normal":0.9816366675185271}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8160656000000001,"event_time":"2026-02-18T12:00:10+00:00","arrival_time":"2026-02-18T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.18393439999999994,"normal":0.8160656000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-18T12:00:10+00:00","arrival_time":"2026-02-18T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8160656000000001,"event_time":"2026-02-18T12:00:12+00:00","arrival_time":"2026-02-18T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.18393439999999994,"normal":0.8160656000000001},"reference_distribution":{"anomalous":0.18393439999999994,"normal":0.8160656000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-18T12:00:12+00:00","arrival_time":"2026-02-18T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"weakened","supporting_evidence":["obs-1"],"contradicting_evidence":["obs-2"],"provenance":"robot-1","reference_confidence":0.5495977628528236,"event_time":"2026-02-18T12:00:20+00:00","arrival_time":"2026-02-18T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.18393439999999994,"normal":0.8160656000000001},"reference_distribution":{"anomalous":0.4504022371471764,"normal":0.5495977628528236}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-048-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-2"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-18T12:00:20+00:00","arrival_time":"2026-02-18T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9816366675185271,"event_time":"2026-02-18T12:00:30+00:00","arrival_time":"2026-02-18T12:00:48+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.4504022371471764,"normal":0.5495977628528236},"reference_distribution":{"anomalous":0.018363332481472976,"normal":0.9816366675185271}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-18T12:00:30+00:00","arrival_time":"2026-02-18T12:00:48+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":48,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"818c27b5aa44792a76dbcc24f3d34fed23cb2c93397c52f965770d6f66e25d4f"}}
{"id":"evaluation-v1-contradiction_resolution-20260725-049","name":"Evaluation v1.0 trajectory: contradiction_resolution case 049","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-049","label":"Distractor 049","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.838575,"modality":"semantic_status","timestamp":"2026-02-19T12:00:10Z","metadata":{"arrival_time":"2026-02-19T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.848575,"modality":"semantic_status","timestamp":"2026-02-19T12:00:20Z","metadata":{"arrival_time":"2026-02-19T12:00:20+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.95314,"modality":"semantic_status","timestamp":"2026-02-19T12:00:30Z","metadata":{"arrival_time":"2026-02-19T12:00:49+00:00","state_epoch":1,"supersedes_evidence_ids":["obs-2"],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-049","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-02-19T12:00:13Z","metadata":{"arrival_time":"2026-02-19T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[],"next_action":{"action_type":"monitor","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-3"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-19T12:00:10+00:00","obs-2":"2026-02-19T12:00:20+00:00","obs-3":"2026-02-19T12:00:30+00:00","obs-distractor":"2026-02-19T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-19T12:00:10+00:00","obs-2":"2026-02-19T12:00:20+00:00","obs-3":"2026-02-19T12:00:49+00:00","obs-distractor":"2026-02-19T12:00:13+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.942,"edge-ai-1":0.63},"confidence":{"obs-1":0.838575,"obs-2":0.848575,"obs-3":0.95314,"obs-distractor":0.69},"state_epochs":{"obs-1":1,"obs-2":1,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{"obs-3":["obs-2"]}},"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9607244097458281,"event_time":"2026-02-19T12:00:30+00:00","arrival_time":"2026-02-19T12:00:49+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5774462138760206,"normal":0.4225537861239795},"reference_distribution":{"anomalous":0.03927559025417193,"normal":0.9607244097458281}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.779324375,"event_time":"2026-02-19T12:00:10+00:00","arrival_time":"2026-02-19T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.22067562500000004,"normal":0.779324375}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-19T12:00:10+00:00","arrival_time":"2026-02-19T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.779324375,"event_time":"2026-02-19T12:00:13+00:00","arrival_time":"2026-02-19T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22067562500000004,"normal":0.779324375},"reference_distribution":{"anomalous":0.22067562500000004,"normal":0.779324375}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-19T12:00:13+00:00","arrival_time":"2026-02-19T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"normal","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.5774462138760206,"event_time":"2026-02-19T12:00:20+00:00","arrival_time":"2026-02-19T12:00:20+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.22067562500000004,"normal":0.779324375},"reference_distribution":{"anomalous":0.5774462138760206,"normal":0.4225537861239795}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-049-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-19T12:00:20+00:00","arrival_time":"2026-02-19T12:00:20+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-3"],"stale_evidence_ids":[],"superseded_evidence_ids":["obs-2"],"event_types":["delayed_evidence","contradiction_resolution","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-1","obs-3"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9607244097458281,"event_time":"2026-02-19T12:00:30+00:00","arrival_time":"2026-02-19T12:00:49+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5774462138760206,"normal":0.4225537861239795},"reference_distribution":{"anomalous":0.03927559025417193,"normal":0.9607244097458281}}],"contradictions":[{"contradiction_id":"evaluation-v1-contradiction_resolution-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"resolved","superseded_evidence_ids":["obs-2"]}],"action":{"reference_action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"monitor","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-3"],"acceptable_supporting_evidence":["obs-1","obs-3"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"resolved","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-19T12:00:30+00:00","arrival_time":"2026-02-19T12:00:49+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"contradiction_resolution","case_index":49,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"53265b8da5e9664809bb4a199f8b8c6a747919c47ff95619dfe5e30283e6dfa4"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-000","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 000","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-000","label":"Distractor 000","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.88,"modality":"semantic_status","timestamp":"2026-01-01T12:00:20Z","metadata":{"arrival_time":"2026-01-01T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-000","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-01-01T12:00:12Z","metadata":{"arrival_time":"2026-01-01T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79,"modality":"semantic_status","timestamp":"2026-01-01T12:00:22Z","metadata":{"arrival_time":"2026-01-01T12:00:34+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.97,"modality":"semantic_status","timestamp":"2026-01-01T12:00:05Z","metadata":{"arrival_time":"2026-01-01T12:00:54+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-01T12:00:20+00:00","obs-distractor":"2026-01-01T12:00:12+00:00","obs-2":"2026-01-01T12:00:22+00:00","obs-3":"2026-01-01T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-01-01T12:00:10+00:00","obs-distractor":"2026-01-01T12:00:12+00:00","obs-2":"2026-01-01T12:00:34+00:00","obs-3":"2026-01-01T12:00:54+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.91,"edge-ai-1":0.52},"confidence":{"obs-1":0.88,"obs-distractor":0.6,"obs-2":0.79,"obs-3":0.97},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9267717295438096,"event_time":"2026-01-01T12:00:05+00:00","arrival_time":"2026-01-01T12:00:54+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9267717295438096,"normal":0.07322827045619042},"reference_distribution":{"anomalous":0.9267717295438096,"normal":0.07322827045619042}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7964,"event_time":"2026-01-01T12:00:20+00:00","arrival_time":"2026-01-01T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.7964,"normal":0.2036}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-01T12:00:20+00:00","arrival_time":"2026-01-01T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7964,"event_time":"2026-01-01T12:00:12+00:00","arrival_time":"2026-01-01T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7964,"normal":0.2036},"reference_distribution":{"anomalous":0.7964,"normal":0.2036}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-01T12:00:12+00:00","arrival_time":"2026-01-01T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9267717295438096,"event_time":"2026-01-01T12:00:22+00:00","arrival_time":"2026-01-01T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7964,"normal":0.2036},"reference_distribution":{"anomalous":0.9267717295438096,"normal":0.07322827045619042}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-01T12:00:22+00:00","arrival_time":"2026-01-01T12:00:34+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9267717295438096,"event_time":"2026-01-01T12:00:05+00:00","arrival_time":"2026-01-01T12:00:54+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9267717295438096,"normal":0.07322827045619042},"reference_distribution":{"anomalous":0.9267717295438096,"normal":0.07322827045619042}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-01T12:00:05+00:00","arrival_time":"2026-01-01T12:00:54+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":0,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"d89dc42b573fad25e1a6bae45dd1bad72b004f73a8fb1495c6dc510b8abc4c4b"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-001","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 001","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-001","label":"Distractor 001","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.880175,"modality":"semantic_status","timestamp":"2026-01-02T12:00:20Z","metadata":{"arrival_time":"2026-01-02T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-001","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-01-02T12:00:13Z","metadata":{"arrival_time":"2026-01-02T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79014,"modality":"semantic_status","timestamp":"2026-01-02T12:00:22Z","metadata":{"arrival_time":"2026-01-02T12:00:35+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96986,"modality":"semantic_status","timestamp":"2026-01-02T12:00:05Z","metadata":{"arrival_time":"2026-01-02T12:00:55+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-01-02T12:00:20+00:00","obs-distractor":"2026-01-02T12:00:13+00:00","obs-2":"2026-01-02T12:00:22+00:00","obs-3":"2026-01-02T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-01-02T12:00:10+00:00","obs-distractor":"2026-01-02T12:00:13+00:00","obs-2":"2026-01-02T12:00:35+00:00","obs-3":"2026-01-02T12:00:55+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.918,"edge-ai-1":0.531},"confidence":{"obs-1":0.880175,"obs-distractor":0.61,"obs-2":0.79014,"obs-3":0.96986},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9379605113936927,"event_time":"2026-01-02T12:00:05+00:00","arrival_time":"2026-01-02T12:00:55+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9379605113936927,"normal":0.0620394886063073},"reference_distribution":{"anomalous":0.9379605113936927,"normal":0.0620394886063073}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.84900065,"event_time":"2026-01-02T12:00:20+00:00","arrival_time":"2026-01-02T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.84900065,"normal":0.15099934999999998}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-02T12:00:20+00:00","arrival_time":"2026-01-02T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.84900065,"event_time":"2026-01-02T12:00:13+00:00","arrival_time":"2026-01-02T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.84900065,"normal":0.15099934999999998},"reference_distribution":{"anomalous":0.84900065,"normal":0.15099934999999998}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-02T12:00:13+00:00","arrival_time":"2026-01-02T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9379605113936927,"event_time":"2026-01-02T12:00:22+00:00","arrival_time":"2026-01-02T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.84900065,"normal":0.15099934999999998},"reference_distribution":{"anomalous":0.9379605113936927,"normal":0.0620394886063073}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-02T12:00:22+00:00","arrival_time":"2026-01-02T12:00:35+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9379605113936927,"event_time":"2026-01-02T12:00:05+00:00","arrival_time":"2026-01-02T12:00:55+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9379605113936927,"normal":0.0620394886063073},"reference_distribution":{"anomalous":0.9379605113936927,"normal":0.0620394886063073}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-02T12:00:05+00:00","arrival_time":"2026-01-02T12:00:55+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":1,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"08798107a842be495cefc2a907ae5beb5033d5455c9930f6c39b60570e423e04"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-002","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 002","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-002","label":"Distractor 002","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.88035,"modality":"semantic_status","timestamp":"2026-01-03T12:00:20Z","metadata":{"arrival_time":"2026-01-03T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79028,"modality":"semantic_status","timestamp":"2026-01-03T12:00:22Z","metadata":{"arrival_time":"2026-01-03T12:00:36+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96972,"modality":"semantic_status","timestamp":"2026-01-03T12:00:05Z","metadata":{"arrival_time":"2026-01-03T12:00:56+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-002","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-01-03T12:00:14Z","metadata":{"arrival_time":"2026-01-03T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-03T12:00:20+00:00","obs-2":"2026-01-03T12:00:22+00:00","obs-3":"2026-01-03T12:00:05+00:00","obs-distractor":"2026-01-03T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-03T12:00:10+00:00","obs-2":"2026-01-03T12:00:36+00:00","obs-3":"2026-01-03T12:00:56+00:00","obs-distractor":"2026-01-03T12:00:14+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.926,"edge-ai-1":0.542},"confidence":{"obs-1":0.88035,"obs-2":0.79028,"obs-3":0.96972,"obs-distractor":0.62},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9315011627290789,"event_time":"2026-01-03T12:00:05+00:00","arrival_time":"2026-01-03T12:00:56+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9315011627290789,"normal":0.06849883727092108},"reference_distribution":{"anomalous":0.9315011627290789,"normal":0.06849883727092108}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8035193,"event_time":"2026-01-03T12:00:20+00:00","arrival_time":"2026-01-03T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8035193,"normal":0.19648069999999995}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-03T12:00:20+00:00","arrival_time":"2026-01-03T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8035193,"event_time":"2026-01-03T12:00:14+00:00","arrival_time":"2026-01-03T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8035193,"normal":0.19648069999999995},"reference_distribution":{"anomalous":0.8035193,"normal":0.19648069999999995}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-03T12:00:14+00:00","arrival_time":"2026-01-03T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9315011627290789,"event_time":"2026-01-03T12:00:22+00:00","arrival_time":"2026-01-03T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8035193,"normal":0.19648069999999995},"reference_distribution":{"anomalous":0.9315011627290789,"normal":0.06849883727092108}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-03T12:00:22+00:00","arrival_time":"2026-01-03T12:00:36+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9315011627290789,"event_time":"2026-01-03T12:00:05+00:00","arrival_time":"2026-01-03T12:00:56+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9315011627290789,"normal":0.06849883727092108},"reference_distribution":{"anomalous":0.9315011627290789,"normal":0.06849883727092108}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-03T12:00:05+00:00","arrival_time":"2026-01-03T12:00:56+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":2,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"0c89a33d3c6fe242d8ebe2391afc6e99689ec6f42521aa83dd6ea14630de9d4b"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-003","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 003","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-003","label":"Distractor 003","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.880525,"modality":"semantic_status","timestamp":"2026-01-04T12:00:20Z","metadata":{"arrival_time":"2026-01-04T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-003","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-01-04T12:00:12Z","metadata":{"arrival_time":"2026-01-04T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79042,"modality":"semantic_status","timestamp":"2026-01-04T12:00:22Z","metadata":{"arrival_time":"2026-01-04T12:00:37+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96958,"modality":"semantic_status","timestamp":"2026-01-04T12:00:05Z","metadata":{"arrival_time":"2026-01-04T12:00:57+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-01-04T12:00:20+00:00","obs-distractor":"2026-01-04T12:00:12+00:00","obs-2":"2026-01-04T12:00:22+00:00","obs-3":"2026-01-04T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-01-04T12:00:10+00:00","obs-distractor":"2026-01-04T12:00:12+00:00","obs-2":"2026-01-04T12:00:37+00:00","obs-3":"2026-01-04T12:00:57+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.934,"edge-ai-1":0.553},"confidence":{"obs-1":0.880525,"obs-distractor":0.63,"obs-2":0.79042,"obs-3":0.96958},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9423824921082216,"event_time":"2026-01-04T12:00:05+00:00","arrival_time":"2026-01-04T12:00:57+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9423824921082216,"normal":0.05761750789177836},"reference_distribution":{"anomalous":0.9423824921082216,"normal":0.05761750789177836}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8554103500000001,"event_time":"2026-01-04T12:00:20+00:00","arrival_time":"2026-01-04T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8554103500000001,"normal":0.1445896499999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-04T12:00:20+00:00","arrival_time":"2026-01-04T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8554103500000001,"event_time":"2026-01-04T12:00:12+00:00","arrival_time":"2026-01-04T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8554103500000001,"normal":0.1445896499999999},"reference_distribution":{"anomalous":0.8554103500000001,"normal":0.1445896499999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-04T12:00:12+00:00","arrival_time":"2026-01-04T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9423824921082216,"event_time":"2026-01-04T12:00:22+00:00","arrival_time":"2026-01-04T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8554103500000001,"normal":0.1445896499999999},"reference_distribution":{"anomalous":0.9423824921082216,"normal":0.05761750789177836}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-04T12:00:22+00:00","arrival_time":"2026-01-04T12:00:37+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9423824921082216,"event_time":"2026-01-04T12:00:05+00:00","arrival_time":"2026-01-04T12:00:57+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9423824921082216,"normal":0.05761750789177836},"reference_distribution":{"anomalous":0.9423824921082216,"normal":0.05761750789177836}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-04T12:00:05+00:00","arrival_time":"2026-01-04T12:00:57+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":3,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"eecf01f870e6d7e5f1d6381367e320b668fa835346edd1e49c762dc3890442f7"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-004","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 004","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-004","label":"Distractor 004","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8807,"modality":"semantic_status","timestamp":"2026-01-05T12:00:20Z","metadata":{"arrival_time":"2026-01-05T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79056,"modality":"semantic_status","timestamp":"2026-01-05T12:00:22Z","metadata":{"arrival_time":"2026-01-05T12:00:38+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96944,"modality":"semantic_status","timestamp":"2026-01-05T12:00:05Z","metadata":{"arrival_time":"2026-01-05T12:00:58+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-004","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-01-05T12:00:13Z","metadata":{"arrival_time":"2026-01-05T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-05T12:00:20+00:00","obs-2":"2026-01-05T12:00:22+00:00","obs-3":"2026-01-05T12:00:05+00:00","obs-distractor":"2026-01-05T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-05T12:00:10+00:00","obs-2":"2026-01-05T12:00:38+00:00","obs-3":"2026-01-05T12:00:58+00:00","obs-distractor":"2026-01-05T12:00:13+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.942,"edge-ai-1":0.564},"confidence":{"obs-1":0.8807,"obs-2":0.79056,"obs-3":0.96944,"obs-distractor":0.64},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.936052711130257,"event_time":"2026-01-05T12:00:05+00:00","arrival_time":"2026-01-05T12:00:58+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.936052711130257,"normal":0.06394728886974302},"reference_distribution":{"anomalous":0.936052711130257,"normal":0.06394728886974302}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8106512,"event_time":"2026-01-05T12:00:20+00:00","arrival_time":"2026-01-05T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8106512,"normal":0.18934879999999998}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-05T12:00:20+00:00","arrival_time":"2026-01-05T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8106512,"event_time":"2026-01-05T12:00:13+00:00","arrival_time":"2026-01-05T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8106512,"normal":0.18934879999999998},"reference_distribution":{"anomalous":0.8106512,"normal":0.18934879999999998}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-05T12:00:13+00:00","arrival_time":"2026-01-05T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.936052711130257,"event_time":"2026-01-05T12:00:22+00:00","arrival_time":"2026-01-05T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8106512,"normal":0.18934879999999998},"reference_distribution":{"anomalous":0.936052711130257,"normal":0.06394728886974302}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-05T12:00:22+00:00","arrival_time":"2026-01-05T12:00:38+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.936052711130257,"event_time":"2026-01-05T12:00:05+00:00","arrival_time":"2026-01-05T12:00:58+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.936052711130257,"normal":0.06394728886974302},"reference_distribution":{"anomalous":0.936052711130257,"normal":0.06394728886974302}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-05T12:00:05+00:00","arrival_time":"2026-01-05T12:00:58+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":4,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"68a1d043f92d38e88ce4f0a68c572fa3a95a038f6cb2ede1975004b5cb964811"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-005","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 005","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-005","label":"Distractor 005","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.880875,"modality":"semantic_status","timestamp":"2026-01-06T12:00:20Z","metadata":{"arrival_time":"2026-01-06T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-005","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-01-06T12:00:14Z","metadata":{"arrival_time":"2026-01-06T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.7907,"modality":"semantic_status","timestamp":"2026-01-06T12:00:22Z","metadata":{"arrival_time":"2026-01-06T12:00:39+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9693,"modality":"semantic_status","timestamp":"2026-01-06T12:00:05Z","metadata":{"arrival_time":"2026-01-06T12:00:59+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-01-06T12:00:20+00:00","obs-distractor":"2026-01-06T12:00:14+00:00","obs-2":"2026-01-06T12:00:22+00:00","obs-3":"2026-01-06T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-01-06T12:00:10+00:00","obs-distractor":"2026-01-06T12:00:14+00:00","obs-2":"2026-01-06T12:00:39+00:00","obs-3":"2026-01-06T12:00:59+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.95,"edge-ai-1":0.575},"confidence":{"obs-1":0.880875,"obs-distractor":0.65,"obs-2":0.7907,"obs-3":0.9693},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9466298171616387,"event_time":"2026-01-06T12:00:05+00:00","arrival_time":"2026-01-06T12:00:59+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9466298171616387,"normal":0.05337018283836125},"reference_distribution":{"anomalous":0.9466298171616387,"normal":0.05337018283836125}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8618312499999999,"event_time":"2026-01-06T12:00:20+00:00","arrival_time":"2026-01-06T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8618312499999999,"normal":0.13816875000000006}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-06T12:00:20+00:00","arrival_time":"2026-01-06T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8618312499999999,"event_time":"2026-01-06T12:00:14+00:00","arrival_time":"2026-01-06T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8618312499999999,"normal":0.13816875000000006},"reference_distribution":{"anomalous":0.8618312499999999,"normal":0.13816875000000006}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-06T12:00:14+00:00","arrival_time":"2026-01-06T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9466298171616387,"event_time":"2026-01-06T12:00:22+00:00","arrival_time":"2026-01-06T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8618312499999999,"normal":0.13816875000000006},"reference_distribution":{"anomalous":0.9466298171616387,"normal":0.05337018283836125}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-06T12:00:22+00:00","arrival_time":"2026-01-06T12:00:39+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9466298171616387,"event_time":"2026-01-06T12:00:05+00:00","arrival_time":"2026-01-06T12:00:59+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9466298171616387,"normal":0.05337018283836125},"reference_distribution":{"anomalous":0.9466298171616387,"normal":0.05337018283836125}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-06T12:00:05+00:00","arrival_time":"2026-01-06T12:00:59+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":5,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"fa6fc2752816e221560bee89f32f03d3e86dd4e7a590ca8a8c9f53af5b13285f"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-006","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 006","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-006","label":"Distractor 006","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.88105,"modality":"semantic_status","timestamp":"2026-01-07T12:00:20Z","metadata":{"arrival_time":"2026-01-07T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79084,"modality":"semantic_status","timestamp":"2026-01-07T12:00:22Z","metadata":{"arrival_time":"2026-01-07T12:00:40+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96916,"modality":"semantic_status","timestamp":"2026-01-07T12:00:05Z","metadata":{"arrival_time":"2026-01-07T12:01:00+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-006","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-01-07T12:00:12Z","metadata":{"arrival_time":"2026-01-07T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-07T12:00:20+00:00","obs-2":"2026-01-07T12:00:22+00:00","obs-3":"2026-01-07T12:00:05+00:00","obs-distractor":"2026-01-07T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-07T12:00:10+00:00","obs-2":"2026-01-07T12:00:40+00:00","obs-3":"2026-01-07T12:01:00+00:00","obs-distractor":"2026-01-07T12:00:12+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.958,"edge-ai-1":0.586},"confidence":{"obs-1":0.88105,"obs-2":0.79084,"obs-3":0.96916,"obs-distractor":0.66},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9404282443838072,"event_time":"2026-01-07T12:00:05+00:00","arrival_time":"2026-01-07T12:01:00+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9404282443838072,"normal":0.059571755616192844},"reference_distribution":{"anomalous":0.9404282443838072,"normal":0.059571755616192844}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8177957,"event_time":"2026-01-07T12:00:20+00:00","arrival_time":"2026-01-07T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8177957,"normal":0.18220429999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-07T12:00:20+00:00","arrival_time":"2026-01-07T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8177957,"event_time":"2026-01-07T12:00:12+00:00","arrival_time":"2026-01-07T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8177957,"normal":0.18220429999999999},"reference_distribution":{"anomalous":0.8177957,"normal":0.18220429999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-07T12:00:12+00:00","arrival_time":"2026-01-07T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9404282443838072,"event_time":"2026-01-07T12:00:22+00:00","arrival_time":"2026-01-07T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8177957,"normal":0.18220429999999999},"reference_distribution":{"anomalous":0.9404282443838072,"normal":0.059571755616192844}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-07T12:00:22+00:00","arrival_time":"2026-01-07T12:00:40+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9404282443838072,"event_time":"2026-01-07T12:00:05+00:00","arrival_time":"2026-01-07T12:01:00+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9404282443838072,"normal":0.059571755616192844},"reference_distribution":{"anomalous":0.9404282443838072,"normal":0.059571755616192844}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-07T12:00:05+00:00","arrival_time":"2026-01-07T12:01:00+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":6,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"7558300bd58fcae08056de6840754fac6d6337941f8b5fbb084c691710797a70"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-007","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 007","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-007","label":"Distractor 007","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.881225,"modality":"semantic_status","timestamp":"2026-01-08T12:00:20Z","metadata":{"arrival_time":"2026-01-08T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-007","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-01-08T12:00:13Z","metadata":{"arrival_time":"2026-01-08T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79098,"modality":"semantic_status","timestamp":"2026-01-08T12:00:22Z","metadata":{"arrival_time":"2026-01-08T12:00:41+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96902,"modality":"semantic_status","timestamp":"2026-01-08T12:00:05Z","metadata":{"arrival_time":"2026-01-08T12:01:01+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-01-08T12:00:20+00:00","obs-distractor":"2026-01-08T12:00:13+00:00","obs-2":"2026-01-08T12:00:22+00:00","obs-3":"2026-01-08T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-01-08T12:00:10+00:00","obs-distractor":"2026-01-08T12:00:13+00:00","obs-2":"2026-01-08T12:00:41+00:00","obs-3":"2026-01-08T12:01:01+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.966,"edge-ai-1":0.597},"confidence":{"obs-1":0.881225,"obs-distractor":0.67,"obs-2":0.79098,"obs-3":0.96902},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9507044920013943,"event_time":"2026-01-08T12:00:05+00:00","arrival_time":"2026-01-08T12:01:01+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9507044920013943,"normal":0.049295507998605784},"reference_distribution":{"anomalous":0.9507044920013943,"normal":0.049295507998605784}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8682633500000001,"event_time":"2026-01-08T12:00:20+00:00","arrival_time":"2026-01-08T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8682633500000001,"normal":0.1317366499999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-08T12:00:20+00:00","arrival_time":"2026-01-08T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8682633500000001,"event_time":"2026-01-08T12:00:13+00:00","arrival_time":"2026-01-08T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8682633500000001,"normal":0.1317366499999999},"reference_distribution":{"anomalous":0.8682633500000001,"normal":0.1317366499999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-08T12:00:13+00:00","arrival_time":"2026-01-08T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9507044920013943,"event_time":"2026-01-08T12:00:22+00:00","arrival_time":"2026-01-08T12:00:41+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8682633500000001,"normal":0.1317366499999999},"reference_distribution":{"anomalous":0.9507044920013943,"normal":0.049295507998605784}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-08T12:00:22+00:00","arrival_time":"2026-01-08T12:00:41+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9507044920013943,"event_time":"2026-01-08T12:00:05+00:00","arrival_time":"2026-01-08T12:01:01+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9507044920013943,"normal":0.049295507998605784},"reference_distribution":{"anomalous":0.9507044920013943,"normal":0.049295507998605784}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-08T12:00:05+00:00","arrival_time":"2026-01-08T12:01:01+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":7,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"442dd44a0ca65274d18b20845a622567e30d8227d00c8bb72b44befeb26fdb99"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-008","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 008","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-008","label":"Distractor 008","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8814,"modality":"semantic_status","timestamp":"2026-01-09T12:00:20Z","metadata":{"arrival_time":"2026-01-09T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-008","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-01-09T12:00:14Z","metadata":{"arrival_time":"2026-01-09T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79112,"modality":"semantic_status","timestamp":"2026-01-09T12:00:22Z","metadata":{"arrival_time":"2026-01-09T12:00:42+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96888,"modality":"semantic_status","timestamp":"2026-01-09T12:00:05Z","metadata":{"arrival_time":"2026-01-09T12:01:02+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-09T12:00:20+00:00","obs-distractor":"2026-01-09T12:00:14+00:00","obs-2":"2026-01-09T12:00:22+00:00","obs-3":"2026-01-09T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-01-09T12:00:10+00:00","obs-distractor":"2026-01-09T12:00:14+00:00","obs-2":"2026-01-09T12:00:42+00:00","obs-3":"2026-01-09T12:01:02+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.974,"edge-ai-1":0.608},"confidence":{"obs-1":0.8814,"obs-distractor":0.68,"obs-2":0.79112,"obs-3":0.96888},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9446297712171048,"event_time":"2026-01-09T12:00:05+00:00","arrival_time":"2026-01-09T12:01:02+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9446297712171048,"normal":0.05537022878289529},"reference_distribution":{"anomalous":0.9446297712171048,"normal":0.05537022878289529}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8249527999999999,"event_time":"2026-01-09T12:00:20+00:00","arrival_time":"2026-01-09T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8249527999999999,"normal":0.17504720000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-09T12:00:20+00:00","arrival_time":"2026-01-09T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8249527999999999,"event_time":"2026-01-09T12:00:14+00:00","arrival_time":"2026-01-09T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8249527999999999,"normal":0.17504720000000007},"reference_distribution":{"anomalous":0.8249527999999999,"normal":0.17504720000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-09T12:00:14+00:00","arrival_time":"2026-01-09T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9446297712171048,"event_time":"2026-01-09T12:00:22+00:00","arrival_time":"2026-01-09T12:00:42+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8249527999999999,"normal":0.17504720000000007},"reference_distribution":{"anomalous":0.9446297712171048,"normal":0.05537022878289529}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-09T12:00:22+00:00","arrival_time":"2026-01-09T12:00:42+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9446297712171048,"event_time":"2026-01-09T12:00:05+00:00","arrival_time":"2026-01-09T12:01:02+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9446297712171048,"normal":0.05537022878289529},"reference_distribution":{"anomalous":0.9446297712171048,"normal":0.05537022878289529}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-09T12:00:05+00:00","arrival_time":"2026-01-09T12:01:02+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":8,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c8fe077d07766a985da8577be7f8a75bd2c21ca871dffd593cfd0d80b402b3e9"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-009","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 009","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-009","label":"Distractor 009","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.881575,"modality":"semantic_status","timestamp":"2026-01-10T12:00:20Z","metadata":{"arrival_time":"2026-01-10T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79126,"modality":"semantic_status","timestamp":"2026-01-10T12:00:22Z","metadata":{"arrival_time":"2026-01-10T12:00:43+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96874,"modality":"semantic_status","timestamp":"2026-01-10T12:00:05Z","metadata":{"arrival_time":"2026-01-10T12:01:03+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-009","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-01-10T12:00:12Z","metadata":{"arrival_time":"2026-01-10T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-10T12:00:20+00:00","obs-2":"2026-01-10T12:00:22+00:00","obs-3":"2026-01-10T12:00:05+00:00","obs-distractor":"2026-01-10T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-10T12:00:10+00:00","obs-2":"2026-01-10T12:00:43+00:00","obs-3":"2026-01-10T12:01:03+00:00","obs-distractor":"2026-01-10T12:00:12+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.91,"edge-ai-1":0.619},"confidence":{"obs-1":0.881575,"obs-2":0.79126,"obs-3":0.96874,"obs-distractor":0.69},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9435243684633301,"event_time":"2026-01-10T12:00:05+00:00","arrival_time":"2026-01-10T12:01:03+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9435243684633301,"normal":0.05647563153666996},"reference_distribution":{"anomalous":0.9435243684633301,"normal":0.05647563153666996}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8472332499999999,"event_time":"2026-01-10T12:00:20+00:00","arrival_time":"2026-01-10T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8472332499999999,"normal":0.15276675000000006}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-10T12:00:20+00:00","arrival_time":"2026-01-10T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8472332499999999,"event_time":"2026-01-10T12:00:12+00:00","arrival_time":"2026-01-10T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8472332499999999,"normal":0.15276675000000006},"reference_distribution":{"anomalous":0.8472332499999999,"normal":0.15276675000000006}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-10T12:00:12+00:00","arrival_time":"2026-01-10T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9435243684633301,"event_time":"2026-01-10T12:00:22+00:00","arrival_time":"2026-01-10T12:00:43+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8472332499999999,"normal":0.15276675000000006},"reference_distribution":{"anomalous":0.9435243684633301,"normal":0.05647563153666996}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-10T12:00:22+00:00","arrival_time":"2026-01-10T12:00:43+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9435243684633301,"event_time":"2026-01-10T12:00:05+00:00","arrival_time":"2026-01-10T12:01:03+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9435243684633301,"normal":0.05647563153666996},"reference_distribution":{"anomalous":0.9435243684633301,"normal":0.05647563153666996}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-10T12:00:05+00:00","arrival_time":"2026-01-10T12:01:03+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":9,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"56649f2540ec4902058155f68a4a72b44fd37dad61991659d2c17b2184972ffe"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-010","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 010","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-010","label":"Distractor 010","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.88175,"modality":"semantic_status","timestamp":"2026-01-11T12:00:20Z","metadata":{"arrival_time":"2026-01-11T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-010","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.7,"modality":"semantic_status","timestamp":"2026-01-11T12:00:13Z","metadata":{"arrival_time":"2026-01-11T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.7914,"modality":"semantic_status","timestamp":"2026-01-11T12:00:22Z","metadata":{"arrival_time":"2026-01-11T12:00:44+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9686,"modality":"semantic_status","timestamp":"2026-01-11T12:00:05Z","metadata":{"arrival_time":"2026-01-11T12:01:04+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-11T12:00:20+00:00","obs-distractor":"2026-01-11T12:00:13+00:00","obs-2":"2026-01-11T12:00:22+00:00","obs-3":"2026-01-11T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-01-11T12:00:10+00:00","obs-distractor":"2026-01-11T12:00:13+00:00","obs-2":"2026-01-11T12:00:44+00:00","obs-3":"2026-01-11T12:01:04+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.918,"edge-ai-1":0.63},"confidence":{"obs-1":0.88175,"obs-distractor":0.7,"obs-2":0.7914,"obs-3":0.9686},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9424062567456681,"event_time":"2026-01-11T12:00:05+00:00","arrival_time":"2026-01-11T12:01:04+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9424062567456681,"normal":0.05759374325433178},"reference_distribution":{"anomalous":0.9424062567456681,"normal":0.05759374325433178}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8321225000000001,"event_time":"2026-01-11T12:00:20+00:00","arrival_time":"2026-01-11T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8321225000000001,"normal":0.1678774999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-11T12:00:20+00:00","arrival_time":"2026-01-11T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8321225000000001,"event_time":"2026-01-11T12:00:13+00:00","arrival_time":"2026-01-11T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8321225000000001,"normal":0.1678774999999999},"reference_distribution":{"anomalous":0.8321225000000001,"normal":0.1678774999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-11T12:00:13+00:00","arrival_time":"2026-01-11T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9424062567456681,"event_time":"2026-01-11T12:00:22+00:00","arrival_time":"2026-01-11T12:00:44+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8321225000000001,"normal":0.1678774999999999},"reference_distribution":{"anomalous":0.9424062567456681,"normal":0.05759374325433178}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-11T12:00:22+00:00","arrival_time":"2026-01-11T12:00:44+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9424062567456681,"event_time":"2026-01-11T12:00:05+00:00","arrival_time":"2026-01-11T12:01:04+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9424062567456681,"normal":0.05759374325433178},"reference_distribution":{"anomalous":0.9424062567456681,"normal":0.05759374325433178}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-11T12:00:05+00:00","arrival_time":"2026-01-11T12:01:04+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":10,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"af57ed56c80c23b6c91b3ee0f77fc3004bf61b0ee2f7fe2d35b2e20ae8d79c97"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-011","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 011","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-011","label":"Distractor 011","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.881925,"modality":"semantic_status","timestamp":"2026-01-12T12:00:20Z","metadata":{"arrival_time":"2026-01-12T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79154,"modality":"semantic_status","timestamp":"2026-01-12T12:00:22Z","metadata":{"arrival_time":"2026-01-12T12:00:45+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96846,"modality":"semantic_status","timestamp":"2026-01-12T12:00:05Z","metadata":{"arrival_time":"2026-01-12T12:01:05+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-011","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.71,"modality":"semantic_status","timestamp":"2026-01-12T12:00:14Z","metadata":{"arrival_time":"2026-01-12T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-12T12:00:20+00:00","obs-2":"2026-01-12T12:00:22+00:00","obs-3":"2026-01-12T12:00:05+00:00","obs-distractor":"2026-01-12T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-12T12:00:10+00:00","obs-2":"2026-01-12T12:00:45+00:00","obs-3":"2026-01-12T12:01:05+00:00","obs-distractor":"2026-01-12T12:00:14+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.926,"edge-ai-1":0.641},"confidence":{"obs-1":0.881925,"obs-2":0.79154,"obs-3":0.96846,"obs-distractor":0.71},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9396358932893075,"event_time":"2026-01-12T12:00:05+00:00","arrival_time":"2026-01-12T12:01:05+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9396358932893075,"normal":0.06036410671069256},"reference_distribution":{"anomalous":0.9396358932893075,"normal":0.06036410671069256}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8536625499999999,"event_time":"2026-01-12T12:00:20+00:00","arrival_time":"2026-01-12T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8536625499999999,"normal":0.1463374500000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-12T12:00:20+00:00","arrival_time":"2026-01-12T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8536625499999999,"event_time":"2026-01-12T12:00:14+00:00","arrival_time":"2026-01-12T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8536625499999999,"normal":0.1463374500000001},"reference_distribution":{"anomalous":0.8536625499999999,"normal":0.1463374500000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-12T12:00:14+00:00","arrival_time":"2026-01-12T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9396358932893075,"event_time":"2026-01-12T12:00:22+00:00","arrival_time":"2026-01-12T12:00:45+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8536625499999999,"normal":0.1463374500000001},"reference_distribution":{"anomalous":0.9396358932893075,"normal":0.06036410671069256}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-12T12:00:22+00:00","arrival_time":"2026-01-12T12:00:45+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9396358932893075,"event_time":"2026-01-12T12:00:05+00:00","arrival_time":"2026-01-12T12:01:05+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9396358932893075,"normal":0.06036410671069256},"reference_distribution":{"anomalous":0.9396358932893075,"normal":0.06036410671069256}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-12T12:00:05+00:00","arrival_time":"2026-01-12T12:01:05+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":11,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"2ec5d327ea543bcb81242b72b63f1332d4b00d33e6036074652c546d0ecd1cc1"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-012","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 012","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-012","label":"Distractor 012","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8821,"modality":"semantic_status","timestamp":"2026-01-13T12:00:20Z","metadata":{"arrival_time":"2026-01-13T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-012","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.72,"modality":"semantic_status","timestamp":"2026-01-13T12:00:12Z","metadata":{"arrival_time":"2026-01-13T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79168,"modality":"semantic_status","timestamp":"2026-01-13T12:00:22Z","metadata":{"arrival_time":"2026-01-13T12:00:46+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96832,"modality":"semantic_status","timestamp":"2026-01-13T12:00:05Z","metadata":{"arrival_time":"2026-01-13T12:01:06+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-13T12:00:20+00:00","obs-distractor":"2026-01-13T12:00:12+00:00","obs-2":"2026-01-13T12:00:22+00:00","obs-3":"2026-01-13T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-01-13T12:00:10+00:00","obs-distractor":"2026-01-13T12:00:12+00:00","obs-2":"2026-01-13T12:00:46+00:00","obs-3":"2026-01-13T12:01:06+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.934,"edge-ai-1":0.652},"confidence":{"obs-1":0.8821,"obs-distractor":0.72,"obs-2":0.79168,"obs-3":0.96832},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9319875820203152,"event_time":"2026-01-13T12:00:05+00:00","arrival_time":"2026-01-13T12:01:06+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9319875820203152,"normal":0.06801241797968484},"reference_distribution":{"anomalous":0.9319875820203152,"normal":0.06801241797968484}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8014768999999999,"event_time":"2026-01-13T12:00:20+00:00","arrival_time":"2026-01-13T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8014768999999999,"normal":0.19852310000000006}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-13T12:00:20+00:00","arrival_time":"2026-01-13T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8014768999999999,"event_time":"2026-01-13T12:00:12+00:00","arrival_time":"2026-01-13T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8014768999999999,"normal":0.19852310000000006},"reference_distribution":{"anomalous":0.8014768999999999,"normal":0.19852310000000006}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-13T12:00:12+00:00","arrival_time":"2026-01-13T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9319875820203152,"event_time":"2026-01-13T12:00:22+00:00","arrival_time":"2026-01-13T12:00:46+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8014768999999999,"normal":0.19852310000000006},"reference_distribution":{"anomalous":0.9319875820203152,"normal":0.06801241797968484}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-13T12:00:22+00:00","arrival_time":"2026-01-13T12:00:46+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9319875820203152,"event_time":"2026-01-13T12:00:05+00:00","arrival_time":"2026-01-13T12:01:06+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9319875820203152,"normal":0.06801241797968484},"reference_distribution":{"anomalous":0.9319875820203152,"normal":0.06801241797968484}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-13T12:00:05+00:00","arrival_time":"2026-01-13T12:01:06+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":12,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"081c7b1174b21bc55d58cf3fba082628a1e5649dd9575ddb6fd9d89bc1d50414"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-013","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 013","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-013","label":"Distractor 013","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.882275,"modality":"semantic_status","timestamp":"2026-01-14T12:00:20Z","metadata":{"arrival_time":"2026-01-14T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79182,"modality":"semantic_status","timestamp":"2026-01-14T12:00:22Z","metadata":{"arrival_time":"2026-01-14T12:00:47+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96818,"modality":"semantic_status","timestamp":"2026-01-14T12:00:05Z","metadata":{"arrival_time":"2026-01-14T12:01:07+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-013","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.73,"modality":"semantic_status","timestamp":"2026-01-14T12:00:13Z","metadata":{"arrival_time":"2026-01-14T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-14T12:00:20+00:00","obs-2":"2026-01-14T12:00:22+00:00","obs-3":"2026-01-14T12:00:05+00:00","obs-distractor":"2026-01-14T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-14T12:00:10+00:00","obs-2":"2026-01-14T12:00:47+00:00","obs-3":"2026-01-14T12:01:07+00:00","obs-distractor":"2026-01-14T12:00:13+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.942,"edge-ai-1":0.52},"confidence":{"obs-1":0.882275,"obs-2":0.79182,"obs-3":0.96818,"obs-distractor":0.73},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9440325874699164,"event_time":"2026-01-14T12:00:05+00:00","arrival_time":"2026-01-14T12:01:07+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9440325874699164,"normal":0.05596741253008368},"reference_distribution":{"anomalous":0.9440325874699164,"normal":0.05596741253008368}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.86010305,"event_time":"2026-01-14T12:00:20+00:00","arrival_time":"2026-01-14T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.86010305,"normal":0.13989695000000002}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-14T12:00:20+00:00","arrival_time":"2026-01-14T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.86010305,"event_time":"2026-01-14T12:00:13+00:00","arrival_time":"2026-01-14T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.86010305,"normal":0.13989695000000002},"reference_distribution":{"anomalous":0.86010305,"normal":0.13989695000000002}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-14T12:00:13+00:00","arrival_time":"2026-01-14T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9440325874699164,"event_time":"2026-01-14T12:00:22+00:00","arrival_time":"2026-01-14T12:00:47+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.86010305,"normal":0.13989695000000002},"reference_distribution":{"anomalous":0.9440325874699164,"normal":0.05596741253008368}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-14T12:00:22+00:00","arrival_time":"2026-01-14T12:00:47+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9440325874699164,"event_time":"2026-01-14T12:00:05+00:00","arrival_time":"2026-01-14T12:01:07+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9440325874699164,"normal":0.05596741253008368},"reference_distribution":{"anomalous":0.9440325874699164,"normal":0.05596741253008368}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-14T12:00:05+00:00","arrival_time":"2026-01-14T12:01:07+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":13,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"e95bc421afdb571d2e57f0ac0e585ce0edddd3412050dc5040f83d5181a2ac69"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-014","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 014","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-014","label":"Distractor 014","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.88245,"modality":"semantic_status","timestamp":"2026-01-15T12:00:20Z","metadata":{"arrival_time":"2026-01-15T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79196,"modality":"semantic_status","timestamp":"2026-01-15T12:00:22Z","metadata":{"arrival_time":"2026-01-15T12:00:48+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96804,"modality":"semantic_status","timestamp":"2026-01-15T12:00:05Z","metadata":{"arrival_time":"2026-01-15T12:01:08+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-014","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.74,"modality":"semantic_status","timestamp":"2026-01-15T12:00:14Z","metadata":{"arrival_time":"2026-01-15T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-15T12:00:20+00:00","obs-2":"2026-01-15T12:00:22+00:00","obs-3":"2026-01-15T12:00:05+00:00","obs-distractor":"2026-01-15T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-15T12:00:10+00:00","obs-2":"2026-01-15T12:00:48+00:00","obs-3":"2026-01-15T12:01:08+00:00","obs-distractor":"2026-01-15T12:00:14+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.95,"edge-ai-1":0.531},"confidence":{"obs-1":0.88245,"obs-2":0.79196,"obs-3":0.96804,"obs-distractor":0.74},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.936525466583863,"event_time":"2026-01-15T12:00:05+00:00","arrival_time":"2026-01-15T12:01:08+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.936525466583863,"normal":0.06347453341613701},"reference_distribution":{"anomalous":0.936525466583863,"normal":0.06347453341613701}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.80863715,"event_time":"2026-01-15T12:00:20+00:00","arrival_time":"2026-01-15T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.80863715,"normal":0.19136284999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-15T12:00:20+00:00","arrival_time":"2026-01-15T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.80863715,"event_time":"2026-01-15T12:00:14+00:00","arrival_time":"2026-01-15T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.80863715,"normal":0.19136284999999997},"reference_distribution":{"anomalous":0.80863715,"normal":0.19136284999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-15T12:00:14+00:00","arrival_time":"2026-01-15T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.936525466583863,"event_time":"2026-01-15T12:00:22+00:00","arrival_time":"2026-01-15T12:00:48+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.80863715,"normal":0.19136284999999997},"reference_distribution":{"anomalous":0.936525466583863,"normal":0.06347453341613701}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-15T12:00:22+00:00","arrival_time":"2026-01-15T12:00:48+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.936525466583863,"event_time":"2026-01-15T12:00:05+00:00","arrival_time":"2026-01-15T12:01:08+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.936525466583863,"normal":0.06347453341613701},"reference_distribution":{"anomalous":0.936525466583863,"normal":0.06347453341613701}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-15T12:00:05+00:00","arrival_time":"2026-01-15T12:01:08+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":14,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"6afef2dc6c2e754af8af339a49b1bb7254e71e9a1dae6ec61aa8b440e967c6df"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-015","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 015","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-015","label":"Distractor 015","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.882625,"modality":"semantic_status","timestamp":"2026-01-16T12:00:20Z","metadata":{"arrival_time":"2026-01-16T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.7921,"modality":"semantic_status","timestamp":"2026-01-16T12:00:22Z","metadata":{"arrival_time":"2026-01-16T12:00:49+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9679,"modality":"semantic_status","timestamp":"2026-01-16T12:00:05Z","metadata":{"arrival_time":"2026-01-16T12:01:09+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-015","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.75,"modality":"semantic_status","timestamp":"2026-01-16T12:00:12Z","metadata":{"arrival_time":"2026-01-16T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-16T12:00:20+00:00","obs-2":"2026-01-16T12:00:22+00:00","obs-3":"2026-01-16T12:00:05+00:00","obs-distractor":"2026-01-16T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-16T12:00:10+00:00","obs-2":"2026-01-16T12:00:49+00:00","obs-3":"2026-01-16T12:01:09+00:00","obs-distractor":"2026-01-16T12:00:12+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.958,"edge-ai-1":0.542},"confidence":{"obs-1":0.882625,"obs-2":0.7921,"obs-3":0.9679,"obs-distractor":0.75},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9482533923047132,"event_time":"2026-01-16T12:00:05+00:00","arrival_time":"2026-01-16T12:01:09+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9482533923047132,"normal":0.05174660769528689},"reference_distribution":{"anomalous":0.9482533923047132,"normal":0.05174660769528689}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8665547499999999,"event_time":"2026-01-16T12:00:20+00:00","arrival_time":"2026-01-16T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8665547499999999,"normal":0.13344525000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-16T12:00:20+00:00","arrival_time":"2026-01-16T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8665547499999999,"event_time":"2026-01-16T12:00:12+00:00","arrival_time":"2026-01-16T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8665547499999999,"normal":0.13344525000000007},"reference_distribution":{"anomalous":0.8665547499999999,"normal":0.13344525000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-16T12:00:12+00:00","arrival_time":"2026-01-16T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9482533923047132,"event_time":"2026-01-16T12:00:22+00:00","arrival_time":"2026-01-16T12:00:49+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8665547499999999,"normal":0.13344525000000007},"reference_distribution":{"anomalous":0.9482533923047132,"normal":0.05174660769528689}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-16T12:00:22+00:00","arrival_time":"2026-01-16T12:00:49+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9482533923047132,"event_time":"2026-01-16T12:00:05+00:00","arrival_time":"2026-01-16T12:01:09+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9482533923047132,"normal":0.05174660769528689},"reference_distribution":{"anomalous":0.9482533923047132,"normal":0.05174660769528689}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-16T12:00:05+00:00","arrival_time":"2026-01-16T12:01:09+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":15,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"29a4faf69c6627026ec5f8cfa5d644ab66f1dd03fca7dec94380339dadb3e708"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-016","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 016","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-016","label":"Distractor 016","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8828,"modality":"semantic_status","timestamp":"2026-01-17T12:00:20Z","metadata":{"arrival_time":"2026-01-17T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79224,"modality":"semantic_status","timestamp":"2026-01-17T12:00:22Z","metadata":{"arrival_time":"2026-01-17T12:00:50+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96776,"modality":"semantic_status","timestamp":"2026-01-17T12:00:05Z","metadata":{"arrival_time":"2026-01-17T12:01:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-016","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.76,"modality":"semantic_status","timestamp":"2026-01-17T12:00:13Z","metadata":{"arrival_time":"2026-01-17T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-17T12:00:20+00:00","obs-2":"2026-01-17T12:00:22+00:00","obs-3":"2026-01-17T12:00:05+00:00","obs-distractor":"2026-01-17T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-17T12:00:10+00:00","obs-2":"2026-01-17T12:00:50+00:00","obs-3":"2026-01-17T12:01:10+00:00","obs-distractor":"2026-01-17T12:00:13+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.966,"edge-ai-1":0.553},"confidence":{"obs-1":0.8828,"obs-2":0.79224,"obs-3":0.96776,"obs-distractor":0.76},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.940886129470671,"event_time":"2026-01-17T12:00:05+00:00","arrival_time":"2026-01-17T12:01:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.940886129470671,"normal":0.059113870529329066},"reference_distribution":{"anomalous":0.940886129470671,"normal":0.059113870529329066}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8158099999999999,"event_time":"2026-01-17T12:00:20+00:00","arrival_time":"2026-01-17T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8158099999999999,"normal":0.18419000000000008}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-17T12:00:20+00:00","arrival_time":"2026-01-17T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8158099999999999,"event_time":"2026-01-17T12:00:13+00:00","arrival_time":"2026-01-17T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8158099999999999,"normal":0.18419000000000008},"reference_distribution":{"anomalous":0.8158099999999999,"normal":0.18419000000000008}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-17T12:00:13+00:00","arrival_time":"2026-01-17T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.940886129470671,"event_time":"2026-01-17T12:00:22+00:00","arrival_time":"2026-01-17T12:00:50+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8158099999999999,"normal":0.18419000000000008},"reference_distribution":{"anomalous":0.940886129470671,"normal":0.059113870529329066}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-17T12:00:22+00:00","arrival_time":"2026-01-17T12:00:50+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.940886129470671,"event_time":"2026-01-17T12:00:05+00:00","arrival_time":"2026-01-17T12:01:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.940886129470671,"normal":0.059113870529329066},"reference_distribution":{"anomalous":0.940886129470671,"normal":0.059113870529329066}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-17T12:00:05+00:00","arrival_time":"2026-01-17T12:01:10+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":16,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"f1b4388472132df634a0cba665ee57941067e69d0994b36ed7e2dd418e37bbb4"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-017","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 017","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-017","label":"Distractor 017","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.882975,"modality":"semantic_status","timestamp":"2026-01-18T12:00:20Z","metadata":{"arrival_time":"2026-01-18T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79238,"modality":"semantic_status","timestamp":"2026-01-18T12:00:22Z","metadata":{"arrival_time":"2026-01-18T12:00:34+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96762,"modality":"semantic_status","timestamp":"2026-01-18T12:00:05Z","metadata":{"arrival_time":"2026-01-18T12:00:54+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-017","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.77,"modality":"semantic_status","timestamp":"2026-01-18T12:00:14Z","metadata":{"arrival_time":"2026-01-18T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-18T12:00:20+00:00","obs-2":"2026-01-18T12:00:22+00:00","obs-3":"2026-01-18T12:00:05+00:00","obs-distractor":"2026-01-18T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-18T12:00:10+00:00","obs-2":"2026-01-18T12:00:34+00:00","obs-3":"2026-01-18T12:00:54+00:00","obs-distractor":"2026-01-18T12:00:14+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.974,"edge-ai-1":0.564},"confidence":{"obs-1":0.882975,"obs-2":0.79238,"obs-3":0.96762,"obs-distractor":0.77},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9523003856304687,"event_time":"2026-01-18T12:00:05+00:00","arrival_time":"2026-01-18T12:00:54+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9523003856304687,"normal":0.047699614369531296},"reference_distribution":{"anomalous":0.9523003856304687,"normal":0.047699614369531296}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87301765,"event_time":"2026-01-18T12:00:20+00:00","arrival_time":"2026-01-18T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.87301765,"normal":0.12698235000000002}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-18T12:00:20+00:00","arrival_time":"2026-01-18T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.87301765,"event_time":"2026-01-18T12:00:14+00:00","arrival_time":"2026-01-18T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.87301765,"normal":0.12698235000000002},"reference_distribution":{"anomalous":0.87301765,"normal":0.12698235000000002}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-18T12:00:14+00:00","arrival_time":"2026-01-18T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9523003856304687,"event_time":"2026-01-18T12:00:22+00:00","arrival_time":"2026-01-18T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.87301765,"normal":0.12698235000000002},"reference_distribution":{"anomalous":0.9523003856304687,"normal":0.047699614369531296}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-18T12:00:22+00:00","arrival_time":"2026-01-18T12:00:34+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9523003856304687,"event_time":"2026-01-18T12:00:05+00:00","arrival_time":"2026-01-18T12:00:54+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9523003856304687,"normal":0.047699614369531296},"reference_distribution":{"anomalous":0.9523003856304687,"normal":0.047699614369531296}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-18T12:00:05+00:00","arrival_time":"2026-01-18T12:00:54+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":17,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"95e67ba7d086c6fc2c0c3a3ce83cfa734749c8a38d6997a282bf5853721b738d"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-018","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 018","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-018","label":"Distractor 018","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.88315,"modality":"semantic_status","timestamp":"2026-01-19T12:00:20Z","metadata":{"arrival_time":"2026-01-19T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79252,"modality":"semantic_status","timestamp":"2026-01-19T12:00:22Z","metadata":{"arrival_time":"2026-01-19T12:00:35+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96748,"modality":"semantic_status","timestamp":"2026-01-19T12:00:05Z","metadata":{"arrival_time":"2026-01-19T12:00:55+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-018","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.78,"modality":"semantic_status","timestamp":"2026-01-19T12:00:12Z","metadata":{"arrival_time":"2026-01-19T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-19T12:00:20+00:00","obs-2":"2026-01-19T12:00:22+00:00","obs-3":"2026-01-19T12:00:05+00:00","obs-distractor":"2026-01-19T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-19T12:00:10+00:00","obs-2":"2026-01-19T12:00:35+00:00","obs-3":"2026-01-19T12:00:55+00:00","obs-distractor":"2026-01-19T12:00:12+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.91,"edge-ai-1":0.575},"confidence":{"obs-1":0.88315,"obs-2":0.79252,"obs-3":0.96748,"obs-distractor":0.78},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9384115618548634,"event_time":"2026-01-19T12:00:05+00:00","arrival_time":"2026-01-19T12:00:55+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9384115618548634,"normal":0.061588438145136565},"reference_distribution":{"anomalous":0.9384115618548634,"normal":0.061588438145136565}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.82299545,"event_time":"2026-01-19T12:00:20+00:00","arrival_time":"2026-01-19T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.82299545,"normal":0.17700455000000004}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-19T12:00:20+00:00","arrival_time":"2026-01-19T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.82299545,"event_time":"2026-01-19T12:00:12+00:00","arrival_time":"2026-01-19T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.82299545,"normal":0.17700455000000004},"reference_distribution":{"anomalous":0.82299545,"normal":0.17700455000000004}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-19T12:00:12+00:00","arrival_time":"2026-01-19T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9384115618548634,"event_time":"2026-01-19T12:00:22+00:00","arrival_time":"2026-01-19T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.82299545,"normal":0.17700455000000004},"reference_distribution":{"anomalous":0.9384115618548634,"normal":0.061588438145136565}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-19T12:00:22+00:00","arrival_time":"2026-01-19T12:00:35+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9384115618548634,"event_time":"2026-01-19T12:00:05+00:00","arrival_time":"2026-01-19T12:00:55+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9384115618548634,"normal":0.061588438145136565},"reference_distribution":{"anomalous":0.9384115618548634,"normal":0.061588438145136565}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-19T12:00:05+00:00","arrival_time":"2026-01-19T12:00:55+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":18,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"e9a8dffb0d2a2accd28a8d80ac513d439f63283a099b0c7e5cd0daa4cce35d00"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-019","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 019","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-019","label":"Distractor 019","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.883325,"modality":"semantic_status","timestamp":"2026-01-20T12:00:20Z","metadata":{"arrival_time":"2026-01-20T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79266,"modality":"semantic_status","timestamp":"2026-01-20T12:00:22Z","metadata":{"arrival_time":"2026-01-20T12:00:36+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96734,"modality":"semantic_status","timestamp":"2026-01-20T12:00:05Z","metadata":{"arrival_time":"2026-01-20T12:00:56+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-019","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.79,"modality":"semantic_status","timestamp":"2026-01-20T12:00:13Z","metadata":{"arrival_time":"2026-01-20T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-20T12:00:20+00:00","obs-2":"2026-01-20T12:00:22+00:00","obs-3":"2026-01-20T12:00:05+00:00","obs-distractor":"2026-01-20T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-20T12:00:10+00:00","obs-2":"2026-01-20T12:00:36+00:00","obs-3":"2026-01-20T12:00:56+00:00","obs-distractor":"2026-01-20T12:00:13+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.918,"edge-ai-1":0.586},"confidence":{"obs-1":0.883325,"obs-2":0.79266,"obs-3":0.96734,"obs-distractor":0.79},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9450414654961254,"event_time":"2026-01-20T12:00:05+00:00","arrival_time":"2026-01-20T12:00:56+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9450414654961254,"normal":0.05495853450387453},"reference_distribution":{"anomalous":0.9450414654961254,"normal":0.05495853450387453}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.85189235,"event_time":"2026-01-20T12:00:20+00:00","arrival_time":"2026-01-20T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.85189235,"normal":0.14810765000000004}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-20T12:00:20+00:00","arrival_time":"2026-01-20T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.85189235,"event_time":"2026-01-20T12:00:13+00:00","arrival_time":"2026-01-20T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.85189235,"normal":0.14810765000000004},"reference_distribution":{"anomalous":0.85189235,"normal":0.14810765000000004}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-20T12:00:13+00:00","arrival_time":"2026-01-20T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9450414654961254,"event_time":"2026-01-20T12:00:22+00:00","arrival_time":"2026-01-20T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.85189235,"normal":0.14810765000000004},"reference_distribution":{"anomalous":0.9450414654961254,"normal":0.05495853450387453}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-20T12:00:22+00:00","arrival_time":"2026-01-20T12:00:36+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9450414654961254,"event_time":"2026-01-20T12:00:05+00:00","arrival_time":"2026-01-20T12:00:56+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9450414654961254,"normal":0.05495853450387453},"reference_distribution":{"anomalous":0.9450414654961254,"normal":0.05495853450387453}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-20T12:00:05+00:00","arrival_time":"2026-01-20T12:00:56+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":19,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"da350dd73eca34a59d3a1b75795a80fc9ad2acd87aefba6b39149e39564fabaf"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-020","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 020","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-020","label":"Distractor 020","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8835,"modality":"semantic_status","timestamp":"2026-01-21T12:00:20Z","metadata":{"arrival_time":"2026-01-21T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.7928,"modality":"semantic_status","timestamp":"2026-01-21T12:00:22Z","metadata":{"arrival_time":"2026-01-21T12:00:37+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9672,"modality":"semantic_status","timestamp":"2026-01-21T12:00:05Z","metadata":{"arrival_time":"2026-01-21T12:00:57+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-020","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-01-21T12:00:14Z","metadata":{"arrival_time":"2026-01-21T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-21T12:00:20+00:00","obs-2":"2026-01-21T12:00:22+00:00","obs-3":"2026-01-21T12:00:05+00:00","obs-distractor":"2026-01-21T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-21T12:00:10+00:00","obs-2":"2026-01-21T12:00:37+00:00","obs-3":"2026-01-21T12:00:57+00:00","obs-distractor":"2026-01-21T12:00:14+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.926,"edge-ai-1":0.597},"confidence":{"obs-1":0.8835,"obs-2":0.7928,"obs-3":0.9672,"obs-distractor":0.6},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9427685873703634,"event_time":"2026-01-21T12:00:05+00:00","arrival_time":"2026-01-21T12:00:57+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9427685873703634,"normal":0.05723141262963667},"reference_distribution":{"anomalous":0.9427685873703634,"normal":0.05723141262963667}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8301935,"event_time":"2026-01-21T12:00:20+00:00","arrival_time":"2026-01-21T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8301935,"normal":0.16980649999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-21T12:00:20+00:00","arrival_time":"2026-01-21T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8301935,"event_time":"2026-01-21T12:00:14+00:00","arrival_time":"2026-01-21T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8301935,"normal":0.16980649999999997},"reference_distribution":{"anomalous":0.8301935,"normal":0.16980649999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-21T12:00:14+00:00","arrival_time":"2026-01-21T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9427685873703634,"event_time":"2026-01-21T12:00:22+00:00","arrival_time":"2026-01-21T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8301935,"normal":0.16980649999999997},"reference_distribution":{"anomalous":0.9427685873703634,"normal":0.05723141262963667}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-21T12:00:22+00:00","arrival_time":"2026-01-21T12:00:37+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9427685873703634,"event_time":"2026-01-21T12:00:05+00:00","arrival_time":"2026-01-21T12:00:57+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9427685873703634,"normal":0.05723141262963667},"reference_distribution":{"anomalous":0.9427685873703634,"normal":0.05723141262963667}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-21T12:00:05+00:00","arrival_time":"2026-01-21T12:00:57+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":20,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"870964d39143bf51998ac08a9aa3c9ba6f04cbe26f6793a8812dc45fb98b7202"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-021","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 021","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-021","label":"Distractor 021","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.883675,"modality":"semantic_status","timestamp":"2026-01-22T12:00:20Z","metadata":{"arrival_time":"2026-01-22T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79294,"modality":"semantic_status","timestamp":"2026-01-22T12:00:22Z","metadata":{"arrival_time":"2026-01-22T12:00:38+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96706,"modality":"semantic_status","timestamp":"2026-01-22T12:00:05Z","metadata":{"arrival_time":"2026-01-22T12:00:58+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-021","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-01-22T12:00:12Z","metadata":{"arrival_time":"2026-01-22T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-22T12:00:20+00:00","obs-2":"2026-01-22T12:00:22+00:00","obs-3":"2026-01-22T12:00:05+00:00","obs-distractor":"2026-01-22T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-22T12:00:10+00:00","obs-2":"2026-01-22T12:00:38+00:00","obs-3":"2026-01-22T12:00:58+00:00","obs-distractor":"2026-01-22T12:00:12+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.934,"edge-ai-1":0.608},"confidence":{"obs-1":0.883675,"obs-2":0.79294,"obs-3":0.96706,"obs-distractor":0.61},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9491344121476906,"event_time":"2026-01-22T12:00:05+00:00","arrival_time":"2026-01-22T12:00:58+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9491344121476906,"normal":0.0508655878523095},"reference_distribution":{"anomalous":0.9491344121476906,"normal":0.0508655878523095}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8583524499999999,"event_time":"2026-01-22T12:00:20+00:00","arrival_time":"2026-01-22T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8583524499999999,"normal":0.14164755000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-22T12:00:20+00:00","arrival_time":"2026-01-22T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8583524499999999,"event_time":"2026-01-22T12:00:12+00:00","arrival_time":"2026-01-22T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8583524499999999,"normal":0.14164755000000007},"reference_distribution":{"anomalous":0.8583524499999999,"normal":0.14164755000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-22T12:00:12+00:00","arrival_time":"2026-01-22T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9491344121476906,"event_time":"2026-01-22T12:00:22+00:00","arrival_time":"2026-01-22T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8583524499999999,"normal":0.14164755000000007},"reference_distribution":{"anomalous":0.9491344121476906,"normal":0.0508655878523095}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-22T12:00:22+00:00","arrival_time":"2026-01-22T12:00:38+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9491344121476906,"event_time":"2026-01-22T12:00:05+00:00","arrival_time":"2026-01-22T12:00:58+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9491344121476906,"normal":0.0508655878523095},"reference_distribution":{"anomalous":0.9491344121476906,"normal":0.0508655878523095}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-22T12:00:05+00:00","arrival_time":"2026-01-22T12:00:58+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":21,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"5b7210d4007b5a5826768ad31b5f7ecae5697c8fc01f48dea6e9dad7bb373ea2"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-022","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 022","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-022","label":"Distractor 022","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.88385,"modality":"semantic_status","timestamp":"2026-01-23T12:00:20Z","metadata":{"arrival_time":"2026-01-23T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-022","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-01-23T12:00:13Z","metadata":{"arrival_time":"2026-01-23T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79308,"modality":"semantic_status","timestamp":"2026-01-23T12:00:22Z","metadata":{"arrival_time":"2026-01-23T12:00:39+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96692,"modality":"semantic_status","timestamp":"2026-01-23T12:00:05Z","metadata":{"arrival_time":"2026-01-23T12:00:59+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-23T12:00:20+00:00","obs-distractor":"2026-01-23T12:00:13+00:00","obs-2":"2026-01-23T12:00:22+00:00","obs-3":"2026-01-23T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-01-23T12:00:10+00:00","obs-distractor":"2026-01-23T12:00:13+00:00","obs-2":"2026-01-23T12:00:39+00:00","obs-3":"2026-01-23T12:00:59+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.942,"edge-ai-1":0.619},"confidence":{"obs-1":0.88385,"obs-distractor":0.62,"obs-2":0.79308,"obs-3":0.96692},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9324874299049161,"event_time":"2026-01-23T12:00:05+00:00","arrival_time":"2026-01-23T12:00:59+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9324874299049161,"normal":0.06751257009508403},"reference_distribution":{"anomalous":0.9324874299049161,"normal":0.06751257009508403}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.7994030000000001,"event_time":"2026-01-23T12:00:20+00:00","arrival_time":"2026-01-23T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.7994030000000001,"normal":0.20059699999999991}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-23T12:00:20+00:00","arrival_time":"2026-01-23T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7994030000000001,"event_time":"2026-01-23T12:00:13+00:00","arrival_time":"2026-01-23T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7994030000000001,"normal":0.20059699999999991},"reference_distribution":{"anomalous":0.7994030000000001,"normal":0.20059699999999991}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-23T12:00:13+00:00","arrival_time":"2026-01-23T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9324874299049161,"event_time":"2026-01-23T12:00:22+00:00","arrival_time":"2026-01-23T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7994030000000001,"normal":0.20059699999999991},"reference_distribution":{"anomalous":0.9324874299049161,"normal":0.06751257009508403}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-23T12:00:22+00:00","arrival_time":"2026-01-23T12:00:39+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9324874299049161,"event_time":"2026-01-23T12:00:05+00:00","arrival_time":"2026-01-23T12:00:59+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9324874299049161,"normal":0.06751257009508403},"reference_distribution":{"anomalous":0.9324874299049161,"normal":0.06751257009508403}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-23T12:00:05+00:00","arrival_time":"2026-01-23T12:00:59+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":22,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"a0771a4eea3d1d6c8624434bc4f16dfc2130e6a2084efc063d5cbf630b267128"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-023","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 023","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-023","label":"Distractor 023","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.884025,"modality":"semantic_status","timestamp":"2026-01-24T12:00:20Z","metadata":{"arrival_time":"2026-01-24T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79322,"modality":"semantic_status","timestamp":"2026-01-24T12:00:22Z","metadata":{"arrival_time":"2026-01-24T12:00:40+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96678,"modality":"semantic_status","timestamp":"2026-01-24T12:00:05Z","metadata":{"arrival_time":"2026-01-24T12:01:00+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-023","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-01-24T12:00:14Z","metadata":{"arrival_time":"2026-01-24T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-24T12:00:20+00:00","obs-2":"2026-01-24T12:00:22+00:00","obs-3":"2026-01-24T12:00:05+00:00","obs-distractor":"2026-01-24T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-24T12:00:10+00:00","obs-2":"2026-01-24T12:00:40+00:00","obs-3":"2026-01-24T12:01:00+00:00","obs-distractor":"2026-01-24T12:00:14+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.95,"edge-ai-1":0.63},"confidence":{"obs-1":0.884025,"obs-2":0.79322,"obs-3":0.96678,"obs-distractor":0.63},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9457015793209115,"event_time":"2026-01-24T12:00:05+00:00","arrival_time":"2026-01-24T12:01:00+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9457015793209115,"normal":0.05429842067908858},"reference_distribution":{"anomalous":0.9457015793209115,"normal":0.05429842067908858}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.86482375,"event_time":"2026-01-24T12:00:20+00:00","arrival_time":"2026-01-24T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.86482375,"normal":0.13517625}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-24T12:00:20+00:00","arrival_time":"2026-01-24T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.86482375,"event_time":"2026-01-24T12:00:14+00:00","arrival_time":"2026-01-24T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.86482375,"normal":0.13517625},"reference_distribution":{"anomalous":0.86482375,"normal":0.13517625}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-24T12:00:14+00:00","arrival_time":"2026-01-24T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9457015793209115,"event_time":"2026-01-24T12:00:22+00:00","arrival_time":"2026-01-24T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.86482375,"normal":0.13517625},"reference_distribution":{"anomalous":0.9457015793209115,"normal":0.05429842067908858}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-24T12:00:22+00:00","arrival_time":"2026-01-24T12:00:40+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9457015793209115,"event_time":"2026-01-24T12:00:05+00:00","arrival_time":"2026-01-24T12:01:00+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9457015793209115,"normal":0.05429842067908858},"reference_distribution":{"anomalous":0.9457015793209115,"normal":0.05429842067908858}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-24T12:00:05+00:00","arrival_time":"2026-01-24T12:01:00+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":23,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"64ea516c5a3143fac2a5f3120b8f5e32f30338d4bb13ffe58067f37116b85541"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-024","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 024","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-024","label":"Distractor 024","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8842,"modality":"semantic_status","timestamp":"2026-01-25T12:00:20Z","metadata":{"arrival_time":"2026-01-25T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79336,"modality":"semantic_status","timestamp":"2026-01-25T12:00:22Z","metadata":{"arrival_time":"2026-01-25T12:00:41+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96664,"modality":"semantic_status","timestamp":"2026-01-25T12:00:05Z","metadata":{"arrival_time":"2026-01-25T12:01:01+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-024","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-01-25T12:00:12Z","metadata":{"arrival_time":"2026-01-25T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-25T12:00:20+00:00","obs-2":"2026-01-25T12:00:22+00:00","obs-3":"2026-01-25T12:00:05+00:00","obs-distractor":"2026-01-25T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-25T12:00:10+00:00","obs-2":"2026-01-25T12:00:41+00:00","obs-3":"2026-01-25T12:01:01+00:00","obs-distractor":"2026-01-25T12:00:12+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.958,"edge-ai-1":0.641},"confidence":{"obs-1":0.8842,"obs-2":0.79336,"obs-3":0.96664,"obs-distractor":0.64},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9370115483215881,"event_time":"2026-01-25T12:00:05+00:00","arrival_time":"2026-01-25T12:01:01+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9370115483215881,"normal":0.06298845167841197},"reference_distribution":{"anomalous":0.9370115483215881,"normal":0.06298845167841197}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8065916,"event_time":"2026-01-25T12:00:20+00:00","arrival_time":"2026-01-25T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8065916,"normal":0.19340840000000004}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-25T12:00:20+00:00","arrival_time":"2026-01-25T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8065916,"event_time":"2026-01-25T12:00:12+00:00","arrival_time":"2026-01-25T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8065916,"normal":0.19340840000000004},"reference_distribution":{"anomalous":0.8065916,"normal":0.19340840000000004}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-25T12:00:12+00:00","arrival_time":"2026-01-25T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9370115483215881,"event_time":"2026-01-25T12:00:22+00:00","arrival_time":"2026-01-25T12:00:41+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8065916,"normal":0.19340840000000004},"reference_distribution":{"anomalous":0.9370115483215881,"normal":0.06298845167841197}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-25T12:00:22+00:00","arrival_time":"2026-01-25T12:00:41+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9370115483215881,"event_time":"2026-01-25T12:00:05+00:00","arrival_time":"2026-01-25T12:01:01+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9370115483215881,"normal":0.06298845167841197},"reference_distribution":{"anomalous":0.9370115483215881,"normal":0.06298845167841197}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-25T12:00:05+00:00","arrival_time":"2026-01-25T12:01:01+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":24,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"cd51669e3dee3d82bfa0ea29262b510e2a769e448257e04badb27054d5790fa1"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-025","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 025","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-025","label":"Distractor 025","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.884375,"modality":"semantic_status","timestamp":"2026-01-26T12:00:20Z","metadata":{"arrival_time":"2026-01-26T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.7935,"modality":"semantic_status","timestamp":"2026-01-26T12:00:22Z","metadata":{"arrival_time":"2026-01-26T12:00:42+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9665,"modality":"semantic_status","timestamp":"2026-01-26T12:00:05Z","metadata":{"arrival_time":"2026-01-26T12:01:02+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-025","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-01-26T12:00:13Z","metadata":{"arrival_time":"2026-01-26T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-26T12:00:20+00:00","obs-2":"2026-01-26T12:00:22+00:00","obs-3":"2026-01-26T12:00:05+00:00","obs-distractor":"2026-01-26T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-26T12:00:10+00:00","obs-2":"2026-01-26T12:00:42+00:00","obs-3":"2026-01-26T12:01:02+00:00","obs-distractor":"2026-01-26T12:00:13+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.966,"edge-ai-1":0.652},"confidence":{"obs-1":0.884375,"obs-2":0.7935,"obs-3":0.9665,"obs-distractor":0.65},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9498955074711463,"event_time":"2026-01-26T12:00:05+00:00","arrival_time":"2026-01-26T12:01:02+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9498955074711463,"normal":0.050104492528853795},"reference_distribution":{"anomalous":0.9498955074711463,"normal":0.050104492528853795}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87130625,"event_time":"2026-01-26T12:00:20+00:00","arrival_time":"2026-01-26T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.87130625,"normal":0.12869375000000005}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-26T12:00:20+00:00","arrival_time":"2026-01-26T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.87130625,"event_time":"2026-01-26T12:00:13+00:00","arrival_time":"2026-01-26T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.87130625,"normal":0.12869375000000005},"reference_distribution":{"anomalous":0.87130625,"normal":0.12869375000000005}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-26T12:00:13+00:00","arrival_time":"2026-01-26T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9498955074711463,"event_time":"2026-01-26T12:00:22+00:00","arrival_time":"2026-01-26T12:00:42+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.87130625,"normal":0.12869375000000005},"reference_distribution":{"anomalous":0.9498955074711463,"normal":0.050104492528853795}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-26T12:00:22+00:00","arrival_time":"2026-01-26T12:00:42+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9498955074711463,"event_time":"2026-01-26T12:00:05+00:00","arrival_time":"2026-01-26T12:01:02+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9498955074711463,"normal":0.050104492528853795},"reference_distribution":{"anomalous":0.9498955074711463,"normal":0.050104492528853795}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-26T12:00:05+00:00","arrival_time":"2026-01-26T12:01:02+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":25,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"7b6e1b1776fa1325de3707fb39934e1c0914b0a5ad3d54936713e74b39b7c163"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-026","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 026","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-026","label":"Distractor 026","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.88455,"modality":"semantic_status","timestamp":"2026-01-27T12:00:20Z","metadata":{"arrival_time":"2026-01-27T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-026","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-01-27T12:00:14Z","metadata":{"arrival_time":"2026-01-27T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79364,"modality":"semantic_status","timestamp":"2026-01-27T12:00:22Z","metadata":{"arrival_time":"2026-01-27T12:00:43+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96636,"modality":"semantic_status","timestamp":"2026-01-27T12:00:05Z","metadata":{"arrival_time":"2026-01-27T12:01:03+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-27T12:00:20+00:00","obs-distractor":"2026-01-27T12:00:14+00:00","obs-2":"2026-01-27T12:00:22+00:00","obs-3":"2026-01-27T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-01-27T12:00:10+00:00","obs-distractor":"2026-01-27T12:00:14+00:00","obs-2":"2026-01-27T12:00:43+00:00","obs-3":"2026-01-27T12:01:03+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.974,"edge-ai-1":0.52},"confidence":{"obs-1":0.88455,"obs-distractor":0.66,"obs-2":0.79364,"obs-3":0.96636},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9413572298873849,"event_time":"2026-01-27T12:00:05+00:00","arrival_time":"2026-01-27T12:01:03+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9413572298873849,"normal":0.05864277011261508},"reference_distribution":{"anomalous":0.9413572298873849,"normal":0.05864277011261508}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8137927999999999,"event_time":"2026-01-27T12:00:20+00:00","arrival_time":"2026-01-27T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8137927999999999,"normal":0.18620720000000013}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-27T12:00:20+00:00","arrival_time":"2026-01-27T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8137927999999999,"event_time":"2026-01-27T12:00:14+00:00","arrival_time":"2026-01-27T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8137927999999999,"normal":0.18620720000000013},"reference_distribution":{"anomalous":0.8137927999999999,"normal":0.18620720000000013}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-27T12:00:14+00:00","arrival_time":"2026-01-27T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9413572298873849,"event_time":"2026-01-27T12:00:22+00:00","arrival_time":"2026-01-27T12:00:43+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8137927999999999,"normal":0.18620720000000013},"reference_distribution":{"anomalous":0.9413572298873849,"normal":0.05864277011261508}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-27T12:00:22+00:00","arrival_time":"2026-01-27T12:00:43+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9413572298873849,"event_time":"2026-01-27T12:00:05+00:00","arrival_time":"2026-01-27T12:01:03+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9413572298873849,"normal":0.05864277011261508},"reference_distribution":{"anomalous":0.9413572298873849,"normal":0.05864277011261508}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-27T12:00:05+00:00","arrival_time":"2026-01-27T12:01:03+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":26,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"3a07f4d7e256e1a4c978cb207460f5f78ad7f96ba5ff8985f935dfb9869d8acb"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-027","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 027","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-027","label":"Distractor 027","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.884725,"modality":"semantic_status","timestamp":"2026-01-28T12:00:20Z","metadata":{"arrival_time":"2026-01-28T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-027","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-01-28T12:00:12Z","metadata":{"arrival_time":"2026-01-28T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79378,"modality":"semantic_status","timestamp":"2026-01-28T12:00:22Z","metadata":{"arrival_time":"2026-01-28T12:00:44+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96622,"modality":"semantic_status","timestamp":"2026-01-28T12:00:05Z","metadata":{"arrival_time":"2026-01-28T12:01:04+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-01-28T12:00:20+00:00","obs-distractor":"2026-01-28T12:00:12+00:00","obs-2":"2026-01-28T12:00:22+00:00","obs-3":"2026-01-28T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-01-28T12:00:10+00:00","obs-distractor":"2026-01-28T12:00:12+00:00","obs-2":"2026-01-28T12:00:44+00:00","obs-3":"2026-01-28T12:01:04+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.91,"edge-ai-1":0.531},"confidence":{"obs-1":0.884725,"obs-distractor":0.67,"obs-2":0.79378,"obs-3":0.96622},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9423343843221982,"event_time":"2026-01-28T12:00:05+00:00","arrival_time":"2026-01-28T12:01:04+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9423343843221982,"normal":0.057665615677801936},"reference_distribution":{"anomalous":0.9423343843221982,"normal":0.057665615677801936}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.85009975,"event_time":"2026-01-28T12:00:20+00:00","arrival_time":"2026-01-28T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.85009975,"normal":0.14990024999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-28T12:00:20+00:00","arrival_time":"2026-01-28T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.85009975,"event_time":"2026-01-28T12:00:12+00:00","arrival_time":"2026-01-28T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.85009975,"normal":0.14990024999999996},"reference_distribution":{"anomalous":0.85009975,"normal":0.14990024999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-28T12:00:12+00:00","arrival_time":"2026-01-28T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9423343843221982,"event_time":"2026-01-28T12:00:22+00:00","arrival_time":"2026-01-28T12:00:44+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.85009975,"normal":0.14990024999999996},"reference_distribution":{"anomalous":0.9423343843221982,"normal":0.057665615677801936}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-28T12:00:22+00:00","arrival_time":"2026-01-28T12:00:44+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9423343843221982,"event_time":"2026-01-28T12:00:05+00:00","arrival_time":"2026-01-28T12:01:04+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9423343843221982,"normal":0.057665615677801936},"reference_distribution":{"anomalous":0.9423343843221982,"normal":0.057665615677801936}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-28T12:00:05+00:00","arrival_time":"2026-01-28T12:01:04+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":27,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"bca77429353b89bd10ce80270e4485e82cc19561c7db0a8739c5a922c03ad7c1"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-028","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 028","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-028","label":"Distractor 028","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8849,"modality":"semantic_status","timestamp":"2026-01-29T12:00:20Z","metadata":{"arrival_time":"2026-01-29T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-028","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-01-29T12:00:13Z","metadata":{"arrival_time":"2026-01-29T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79392,"modality":"semantic_status","timestamp":"2026-01-29T12:00:22Z","metadata":{"arrival_time":"2026-01-29T12:00:45+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96608,"modality":"semantic_status","timestamp":"2026-01-29T12:00:05Z","metadata":{"arrival_time":"2026-01-29T12:01:05+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-29T12:00:20+00:00","obs-distractor":"2026-01-29T12:00:13+00:00","obs-2":"2026-01-29T12:00:22+00:00","obs-3":"2026-01-29T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-01-29T12:00:10+00:00","obs-distractor":"2026-01-29T12:00:13+00:00","obs-2":"2026-01-29T12:00:45+00:00","obs-3":"2026-01-29T12:01:05+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.918,"edge-ai-1":0.542},"confidence":{"obs-1":0.8849,"obs-distractor":0.68,"obs-2":0.79392,"obs-3":0.96608},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9388007999641902,"event_time":"2026-01-29T12:00:05+00:00","arrival_time":"2026-01-29T12:01:05+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9388007999641902,"normal":0.06119920003580987},"reference_distribution":{"anomalous":0.9388007999641902,"normal":0.06119920003580987}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8210066,"event_time":"2026-01-29T12:00:20+00:00","arrival_time":"2026-01-29T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8210066,"normal":0.17899339999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-29T12:00:20+00:00","arrival_time":"2026-01-29T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8210066,"event_time":"2026-01-29T12:00:13+00:00","arrival_time":"2026-01-29T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8210066,"normal":0.17899339999999997},"reference_distribution":{"anomalous":0.8210066,"normal":0.17899339999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-29T12:00:13+00:00","arrival_time":"2026-01-29T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9388007999641902,"event_time":"2026-01-29T12:00:22+00:00","arrival_time":"2026-01-29T12:00:45+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8210066,"normal":0.17899339999999997},"reference_distribution":{"anomalous":0.9388007999641902,"normal":0.06119920003580987}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-29T12:00:22+00:00","arrival_time":"2026-01-29T12:00:45+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9388007999641902,"event_time":"2026-01-29T12:00:05+00:00","arrival_time":"2026-01-29T12:01:05+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9388007999641902,"normal":0.06119920003580987},"reference_distribution":{"anomalous":0.9388007999641902,"normal":0.06119920003580987}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-29T12:00:05+00:00","arrival_time":"2026-01-29T12:01:05+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":28,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"b5375577b84cdfdb0af130eacdf847209326b21bedec7d0c8bacb4cc6d4a66d0"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-029","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 029","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-029","label":"Distractor 029","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.885075,"modality":"semantic_status","timestamp":"2026-01-30T12:00:20Z","metadata":{"arrival_time":"2026-01-30T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79406,"modality":"semantic_status","timestamp":"2026-01-30T12:00:22Z","metadata":{"arrival_time":"2026-01-30T12:00:46+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96594,"modality":"semantic_status","timestamp":"2026-01-30T12:00:05Z","metadata":{"arrival_time":"2026-01-30T12:01:06+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-029","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-01-30T12:00:14Z","metadata":{"arrival_time":"2026-01-30T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-30T12:00:20+00:00","obs-2":"2026-01-30T12:00:22+00:00","obs-3":"2026-01-30T12:00:05+00:00","obs-distractor":"2026-01-30T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-30T12:00:10+00:00","obs-2":"2026-01-30T12:00:46+00:00","obs-3":"2026-01-30T12:01:06+00:00","obs-distractor":"2026-01-30T12:00:14+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.926,"edge-ai-1":0.553},"confidence":{"obs-1":0.885075,"obs-2":0.79406,"obs-3":0.96594,"obs-distractor":0.69},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9465749260283151,"event_time":"2026-01-30T12:00:05+00:00","arrival_time":"2026-01-30T12:01:06+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9465749260283151,"normal":0.053425073971684875},"reference_distribution":{"anomalous":0.9465749260283151,"normal":0.053425073971684875}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8565794499999999,"event_time":"2026-01-30T12:00:20+00:00","arrival_time":"2026-01-30T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8565794499999999,"normal":0.1434205500000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-30T12:00:20+00:00","arrival_time":"2026-01-30T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8565794499999999,"event_time":"2026-01-30T12:00:14+00:00","arrival_time":"2026-01-30T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8565794499999999,"normal":0.1434205500000001},"reference_distribution":{"anomalous":0.8565794499999999,"normal":0.1434205500000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-30T12:00:14+00:00","arrival_time":"2026-01-30T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9465749260283151,"event_time":"2026-01-30T12:00:22+00:00","arrival_time":"2026-01-30T12:00:46+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8565794499999999,"normal":0.1434205500000001},"reference_distribution":{"anomalous":0.9465749260283151,"normal":0.053425073971684875}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-30T12:00:22+00:00","arrival_time":"2026-01-30T12:00:46+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9465749260283151,"event_time":"2026-01-30T12:00:05+00:00","arrival_time":"2026-01-30T12:01:06+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9465749260283151,"normal":0.053425073971684875},"reference_distribution":{"anomalous":0.9465749260283151,"normal":0.053425073971684875}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-30T12:00:05+00:00","arrival_time":"2026-01-30T12:01:06+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":29,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"71cbfc23f2ddf295a73cf462152bb0b16269167d4d984f44b9c3770b29ec8f80"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-030","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 030","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-030","label":"Distractor 030","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.88525,"modality":"semantic_status","timestamp":"2026-01-31T12:00:20Z","metadata":{"arrival_time":"2026-01-31T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-030","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.7,"modality":"semantic_status","timestamp":"2026-01-31T12:00:12Z","metadata":{"arrival_time":"2026-01-31T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.7942,"modality":"semantic_status","timestamp":"2026-01-31T12:00:22Z","metadata":{"arrival_time":"2026-01-31T12:00:47+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9658,"modality":"semantic_status","timestamp":"2026-01-31T12:00:05Z","metadata":{"arrival_time":"2026-01-31T12:01:07+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-31T12:00:20+00:00","obs-distractor":"2026-01-31T12:00:12+00:00","obs-2":"2026-01-31T12:00:22+00:00","obs-3":"2026-01-31T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-01-31T12:00:10+00:00","obs-distractor":"2026-01-31T12:00:12+00:00","obs-2":"2026-01-31T12:00:47+00:00","obs-3":"2026-01-31T12:01:07+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.934,"edge-ai-1":0.564},"confidence":{"obs-1":0.88525,"obs-distractor":0.7,"obs-2":0.7942,"obs-3":0.9658},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9431427050349754,"event_time":"2026-01-31T12:00:05+00:00","arrival_time":"2026-01-31T12:01:07+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9431427050349754,"normal":0.05685729496502447},"reference_distribution":{"anomalous":0.9431427050349754,"normal":0.05685729496502447}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.828233,"event_time":"2026-01-31T12:00:20+00:00","arrival_time":"2026-01-31T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.828233,"normal":0.171767}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-31T12:00:20+00:00","arrival_time":"2026-01-31T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.828233,"event_time":"2026-01-31T12:00:12+00:00","arrival_time":"2026-01-31T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.828233,"normal":0.171767},"reference_distribution":{"anomalous":0.828233,"normal":0.171767}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-31T12:00:12+00:00","arrival_time":"2026-01-31T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9431427050349754,"event_time":"2026-01-31T12:00:22+00:00","arrival_time":"2026-01-31T12:00:47+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.828233,"normal":0.171767},"reference_distribution":{"anomalous":0.9431427050349754,"normal":0.05685729496502447}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-01-31T12:00:22+00:00","arrival_time":"2026-01-31T12:00:47+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9431427050349754,"event_time":"2026-01-31T12:00:05+00:00","arrival_time":"2026-01-31T12:01:07+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9431427050349754,"normal":0.05685729496502447},"reference_distribution":{"anomalous":0.9431427050349754,"normal":0.05685729496502447}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-31T12:00:05+00:00","arrival_time":"2026-01-31T12:01:07+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":30,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"986a0ef43294d62e7d66d58bbb531fabcd99ef30bb951f0cdae75ecc5719b87b"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-031","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 031","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-031","label":"Distractor 031","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.885425,"modality":"semantic_status","timestamp":"2026-02-01T12:00:20Z","metadata":{"arrival_time":"2026-02-01T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79434,"modality":"semantic_status","timestamp":"2026-02-01T12:00:22Z","metadata":{"arrival_time":"2026-02-01T12:00:48+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96566,"modality":"semantic_status","timestamp":"2026-02-01T12:00:05Z","metadata":{"arrival_time":"2026-02-01T12:01:08+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-031","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.71,"modality":"semantic_status","timestamp":"2026-02-01T12:00:13Z","metadata":{"arrival_time":"2026-02-01T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-01T12:00:20+00:00","obs-2":"2026-02-01T12:00:22+00:00","obs-3":"2026-02-01T12:00:05+00:00","obs-distractor":"2026-02-01T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-01T12:00:10+00:00","obs-2":"2026-02-01T12:00:48+00:00","obs-3":"2026-02-01T12:01:08+00:00","obs-distractor":"2026-02-01T12:00:13+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.942,"edge-ai-1":0.575},"confidence":{"obs-1":0.885425,"obs-2":0.79434,"obs-3":0.96566,"obs-distractor":0.71},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9506403045318198,"event_time":"2026-02-01T12:00:05+00:00","arrival_time":"2026-02-01T12:01:08+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9506403045318198,"normal":0.049359695468180184},"reference_distribution":{"anomalous":0.9506403045318198,"normal":0.049359695468180184}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.86307035,"event_time":"2026-02-01T12:00:20+00:00","arrival_time":"2026-02-01T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.86307035,"normal":0.13692965}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-01T12:00:20+00:00","arrival_time":"2026-02-01T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.86307035,"event_time":"2026-02-01T12:00:13+00:00","arrival_time":"2026-02-01T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.86307035,"normal":0.13692965},"reference_distribution":{"anomalous":0.86307035,"normal":0.13692965}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-01T12:00:13+00:00","arrival_time":"2026-02-01T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9506403045318198,"event_time":"2026-02-01T12:00:22+00:00","arrival_time":"2026-02-01T12:00:48+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.86307035,"normal":0.13692965},"reference_distribution":{"anomalous":0.9506403045318198,"normal":0.049359695468180184}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-01T12:00:22+00:00","arrival_time":"2026-02-01T12:00:48+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9506403045318198,"event_time":"2026-02-01T12:00:05+00:00","arrival_time":"2026-02-01T12:01:08+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9506403045318198,"normal":0.049359695468180184},"reference_distribution":{"anomalous":0.9506403045318198,"normal":0.049359695468180184}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-01T12:00:05+00:00","arrival_time":"2026-02-01T12:01:08+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":31,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"4e1b9a16cdc6436f8640c22be30086a33cfbee7a345eb0489c547b102a34afb4"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-032","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 032","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-032","label":"Distractor 032","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8856,"modality":"semantic_status","timestamp":"2026-02-02T12:00:20Z","metadata":{"arrival_time":"2026-02-02T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-032","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.72,"modality":"semantic_status","timestamp":"2026-02-02T12:00:14Z","metadata":{"arrival_time":"2026-02-02T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79448,"modality":"semantic_status","timestamp":"2026-02-02T12:00:22Z","metadata":{"arrival_time":"2026-02-02T12:00:49+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96552,"modality":"semantic_status","timestamp":"2026-02-02T12:00:05Z","metadata":{"arrival_time":"2026-02-02T12:01:09+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-02T12:00:20+00:00","obs-distractor":"2026-02-02T12:00:14+00:00","obs-2":"2026-02-02T12:00:22+00:00","obs-3":"2026-02-02T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-02-02T12:00:10+00:00","obs-distractor":"2026-02-02T12:00:14+00:00","obs-2":"2026-02-02T12:00:49+00:00","obs-3":"2026-02-02T12:01:09+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.95,"edge-ai-1":0.586},"confidence":{"obs-1":0.8856,"obs-distractor":0.72,"obs-2":0.79448,"obs-3":0.96552},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9473080228186732,"event_time":"2026-02-02T12:00:05+00:00","arrival_time":"2026-02-02T12:01:09+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9473080228186732,"normal":0.052691977181326816},"reference_distribution":{"anomalous":0.9473080228186732,"normal":0.052691977181326816}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.835472,"event_time":"2026-02-02T12:00:20+00:00","arrival_time":"2026-02-02T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.835472,"normal":0.164528}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-02T12:00:20+00:00","arrival_time":"2026-02-02T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.835472,"event_time":"2026-02-02T12:00:14+00:00","arrival_time":"2026-02-02T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.835472,"normal":0.164528},"reference_distribution":{"anomalous":0.835472,"normal":0.164528}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-02T12:00:14+00:00","arrival_time":"2026-02-02T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9473080228186732,"event_time":"2026-02-02T12:00:22+00:00","arrival_time":"2026-02-02T12:00:49+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.835472,"normal":0.164528},"reference_distribution":{"anomalous":0.9473080228186732,"normal":0.052691977181326816}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-02T12:00:22+00:00","arrival_time":"2026-02-02T12:00:49+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9473080228186732,"event_time":"2026-02-02T12:00:05+00:00","arrival_time":"2026-02-02T12:01:09+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9473080228186732,"normal":0.052691977181326816},"reference_distribution":{"anomalous":0.9473080228186732,"normal":0.052691977181326816}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-02T12:00:05+00:00","arrival_time":"2026-02-02T12:01:09+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":32,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"338b16bf46200d56cd6bc0d3c27197652844a9af9885e0641463adc6e1c3e9bb"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-033","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 033","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-033","label":"Distractor 033","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.885775,"modality":"semantic_status","timestamp":"2026-02-03T12:00:20Z","metadata":{"arrival_time":"2026-02-03T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79462,"modality":"semantic_status","timestamp":"2026-02-03T12:00:22Z","metadata":{"arrival_time":"2026-02-03T12:00:50+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96538,"modality":"semantic_status","timestamp":"2026-02-03T12:00:05Z","metadata":{"arrival_time":"2026-02-03T12:01:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-033","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.73,"modality":"semantic_status","timestamp":"2026-02-03T12:00:12Z","metadata":{"arrival_time":"2026-02-03T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-03T12:00:20+00:00","obs-2":"2026-02-03T12:00:22+00:00","obs-3":"2026-02-03T12:00:05+00:00","obs-distractor":"2026-02-03T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-03T12:00:10+00:00","obs-2":"2026-02-03T12:00:50+00:00","obs-3":"2026-02-03T12:01:10+00:00","obs-distractor":"2026-02-03T12:00:12+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.958,"edge-ai-1":0.597},"confidence":{"obs-1":0.885775,"obs-2":0.79462,"obs-3":0.96538,"obs-distractor":0.73},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.947390273596876,"event_time":"2026-02-03T12:00:05+00:00","arrival_time":"2026-02-03T12:01:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.947390273596876,"normal":0.052609726403123974},"reference_distribution":{"anomalous":0.947390273596876,"normal":0.052609726403123974}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8695724499999999,"event_time":"2026-02-03T12:00:20+00:00","arrival_time":"2026-02-03T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8695724499999999,"normal":0.13042755000000006}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-03T12:00:20+00:00","arrival_time":"2026-02-03T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8695724499999999,"event_time":"2026-02-03T12:00:12+00:00","arrival_time":"2026-02-03T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8695724499999999,"normal":0.13042755000000006},"reference_distribution":{"anomalous":0.8695724499999999,"normal":0.13042755000000006}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-03T12:00:12+00:00","arrival_time":"2026-02-03T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.947390273596876,"event_time":"2026-02-03T12:00:22+00:00","arrival_time":"2026-02-03T12:00:50+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8695724499999999,"normal":0.13042755000000006},"reference_distribution":{"anomalous":0.947390273596876,"normal":0.052609726403123974}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-03T12:00:22+00:00","arrival_time":"2026-02-03T12:00:50+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.947390273596876,"event_time":"2026-02-03T12:00:05+00:00","arrival_time":"2026-02-03T12:01:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.947390273596876,"normal":0.052609726403123974},"reference_distribution":{"anomalous":0.947390273596876,"normal":0.052609726403123974}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-03T12:00:05+00:00","arrival_time":"2026-02-03T12:01:10+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":33,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"fdea05fa63fcd987e6f45e996a1801056f90bb61c942489134942450b219d12b"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-034","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 034","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-034","label":"Distractor 034","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.88595,"modality":"semantic_status","timestamp":"2026-02-04T12:00:20Z","metadata":{"arrival_time":"2026-02-04T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-034","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.74,"modality":"semantic_status","timestamp":"2026-02-04T12:00:13Z","metadata":{"arrival_time":"2026-02-04T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79476,"modality":"semantic_status","timestamp":"2026-02-04T12:00:22Z","metadata":{"arrival_time":"2026-02-04T12:00:34+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96524,"modality":"semantic_status","timestamp":"2026-02-04T12:00:05Z","metadata":{"arrival_time":"2026-02-04T12:00:54+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-04T12:00:20+00:00","obs-distractor":"2026-02-04T12:00:13+00:00","obs-2":"2026-02-04T12:00:22+00:00","obs-3":"2026-02-04T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-02-04T12:00:10+00:00","obs-distractor":"2026-02-04T12:00:13+00:00","obs-2":"2026-02-04T12:00:34+00:00","obs-3":"2026-02-04T12:00:54+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.966,"edge-ai-1":0.608},"confidence":{"obs-1":0.88595,"obs-distractor":0.74,"obs-2":0.79476,"obs-3":0.96524},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9375115923107115,"event_time":"2026-02-04T12:00:05+00:00","arrival_time":"2026-02-04T12:00:54+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9375115923107115,"normal":0.062488407689288504},"reference_distribution":{"anomalous":0.9375115923107115,"normal":0.062488407689288504}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.80451455,"event_time":"2026-02-04T12:00:20+00:00","arrival_time":"2026-02-04T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.80451455,"normal":0.19548544999999995}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-04T12:00:20+00:00","arrival_time":"2026-02-04T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.80451455,"event_time":"2026-02-04T12:00:13+00:00","arrival_time":"2026-02-04T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.80451455,"normal":0.19548544999999995},"reference_distribution":{"anomalous":0.80451455,"normal":0.19548544999999995}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-04T12:00:13+00:00","arrival_time":"2026-02-04T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9375115923107115,"event_time":"2026-02-04T12:00:22+00:00","arrival_time":"2026-02-04T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.80451455,"normal":0.19548544999999995},"reference_distribution":{"anomalous":0.9375115923107115,"normal":0.062488407689288504}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-04T12:00:22+00:00","arrival_time":"2026-02-04T12:00:34+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9375115923107115,"event_time":"2026-02-04T12:00:05+00:00","arrival_time":"2026-02-04T12:00:54+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9375115923107115,"normal":0.062488407689288504},"reference_distribution":{"anomalous":0.9375115923107115,"normal":0.062488407689288504}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-04T12:00:05+00:00","arrival_time":"2026-02-04T12:00:54+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":34,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"8effe6569af779ecef2f5dc56c97c5f0e917a1c0068aeaa88ff8228a74ca98b8"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-035","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 035","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-035","label":"Distractor 035","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.886125,"modality":"semantic_status","timestamp":"2026-02-05T12:00:20Z","metadata":{"arrival_time":"2026-02-05T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-035","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.75,"modality":"semantic_status","timestamp":"2026-02-05T12:00:14Z","metadata":{"arrival_time":"2026-02-05T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.7949,"modality":"semantic_status","timestamp":"2026-02-05T12:00:22Z","metadata":{"arrival_time":"2026-02-05T12:00:35+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9651,"modality":"semantic_status","timestamp":"2026-02-05T12:00:05Z","metadata":{"arrival_time":"2026-02-05T12:00:55+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-02-05T12:00:20+00:00","obs-distractor":"2026-02-05T12:00:14+00:00","obs-2":"2026-02-05T12:00:22+00:00","obs-3":"2026-02-05T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-02-05T12:00:10+00:00","obs-distractor":"2026-02-05T12:00:14+00:00","obs-2":"2026-02-05T12:00:35+00:00","obs-3":"2026-02-05T12:00:55+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.974,"edge-ai-1":0.619},"confidence":{"obs-1":0.886125,"obs-distractor":0.75,"obs-2":0.7949,"obs-3":0.9651},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9515569574796551,"event_time":"2026-02-05T12:00:05+00:00","arrival_time":"2026-02-05T12:00:55+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9515569574796551,"normal":0.04844304252034482},"reference_distribution":{"anomalous":0.9515569574796551,"normal":0.04844304252034482}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8760857500000001,"event_time":"2026-02-05T12:00:20+00:00","arrival_time":"2026-02-05T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8760857500000001,"normal":0.12391424999999989}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-05T12:00:20+00:00","arrival_time":"2026-02-05T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8760857500000001,"event_time":"2026-02-05T12:00:14+00:00","arrival_time":"2026-02-05T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8760857500000001,"normal":0.12391424999999989},"reference_distribution":{"anomalous":0.8760857500000001,"normal":0.12391424999999989}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-05T12:00:14+00:00","arrival_time":"2026-02-05T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9515569574796551,"event_time":"2026-02-05T12:00:22+00:00","arrival_time":"2026-02-05T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8760857500000001,"normal":0.12391424999999989},"reference_distribution":{"anomalous":0.9515569574796551,"normal":0.04844304252034482}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-05T12:00:22+00:00","arrival_time":"2026-02-05T12:00:35+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9515569574796551,"event_time":"2026-02-05T12:00:05+00:00","arrival_time":"2026-02-05T12:00:55+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9515569574796551,"normal":0.04844304252034482},"reference_distribution":{"anomalous":0.9515569574796551,"normal":0.04844304252034482}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-05T12:00:05+00:00","arrival_time":"2026-02-05T12:00:55+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":35,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"a5856291c4831ede053c5b236d0913822cead2d35e697f6e1cad2e0d776a70ec"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-036","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 036","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-036","label":"Distractor 036","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8863,"modality":"semantic_status","timestamp":"2026-02-06T12:00:20Z","metadata":{"arrival_time":"2026-02-06T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79504,"modality":"semantic_status","timestamp":"2026-02-06T12:00:22Z","metadata":{"arrival_time":"2026-02-06T12:00:36+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96496,"modality":"semantic_status","timestamp":"2026-02-06T12:00:05Z","metadata":{"arrival_time":"2026-02-06T12:00:56+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-036","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.76,"modality":"semantic_status","timestamp":"2026-02-06T12:00:12Z","metadata":{"arrival_time":"2026-02-06T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-06T12:00:20+00:00","obs-2":"2026-02-06T12:00:22+00:00","obs-3":"2026-02-06T12:00:05+00:00","obs-distractor":"2026-02-06T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-06T12:00:10+00:00","obs-2":"2026-02-06T12:00:36+00:00","obs-3":"2026-02-06T12:00:56+00:00","obs-distractor":"2026-02-06T12:00:12+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.91,"edge-ai-1":0.63},"confidence":{"obs-1":0.8863,"obs-2":0.79504,"obs-3":0.96496,"obs-distractor":0.76},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9346959468679616,"event_time":"2026-02-06T12:00:05+00:00","arrival_time":"2026-02-06T12:00:56+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9346959468679616,"normal":0.0653040531320384},"reference_distribution":{"anomalous":0.9346959468679616,"normal":0.0653040531320384}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8117441000000001,"event_time":"2026-02-06T12:00:20+00:00","arrival_time":"2026-02-06T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8117441000000001,"normal":0.18825589999999992}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-06T12:00:20+00:00","arrival_time":"2026-02-06T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8117441000000001,"event_time":"2026-02-06T12:00:12+00:00","arrival_time":"2026-02-06T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8117441000000001,"normal":0.18825589999999992},"reference_distribution":{"anomalous":0.8117441000000001,"normal":0.18825589999999992}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-06T12:00:12+00:00","arrival_time":"2026-02-06T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9346959468679616,"event_time":"2026-02-06T12:00:22+00:00","arrival_time":"2026-02-06T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8117441000000001,"normal":0.18825589999999992},"reference_distribution":{"anomalous":0.9346959468679616,"normal":0.0653040531320384}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-06T12:00:22+00:00","arrival_time":"2026-02-06T12:00:36+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9346959468679616,"event_time":"2026-02-06T12:00:05+00:00","arrival_time":"2026-02-06T12:00:56+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9346959468679616,"normal":0.0653040531320384},"reference_distribution":{"anomalous":0.9346959468679616,"normal":0.0653040531320384}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-06T12:00:05+00:00","arrival_time":"2026-02-06T12:00:56+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":36,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"fc8579254383aca46a78d8bc5fab91e12c22b8a54acfa986757e6a3a1bdc0126"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-037","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 037","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-037","label":"Distractor 037","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.886475,"modality":"semantic_status","timestamp":"2026-02-07T12:00:20Z","metadata":{"arrival_time":"2026-02-07T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79518,"modality":"semantic_status","timestamp":"2026-02-07T12:00:22Z","metadata":{"arrival_time":"2026-02-07T12:00:37+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96482,"modality":"semantic_status","timestamp":"2026-02-07T12:00:05Z","metadata":{"arrival_time":"2026-02-07T12:00:57+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-037","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.77,"modality":"semantic_status","timestamp":"2026-02-07T12:00:13Z","metadata":{"arrival_time":"2026-02-07T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-07T12:00:20+00:00","obs-2":"2026-02-07T12:00:22+00:00","obs-3":"2026-02-07T12:00:05+00:00","obs-distractor":"2026-02-07T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-07T12:00:10+00:00","obs-2":"2026-02-07T12:00:37+00:00","obs-3":"2026-02-07T12:00:57+00:00","obs-distractor":"2026-02-07T12:00:13+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.918,"edge-ai-1":0.641},"confidence":{"obs-1":0.886475,"obs-2":0.79518,"obs-3":0.96482,"obs-distractor":0.77},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9439117308986417,"event_time":"2026-02-07T12:00:05+00:00","arrival_time":"2026-02-07T12:00:57+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9439117308986417,"normal":0.056088269101358355},"reference_distribution":{"anomalous":0.9439117308986417,"normal":0.056088269101358355}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.85478405,"event_time":"2026-02-07T12:00:20+00:00","arrival_time":"2026-02-07T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.85478405,"normal":0.14521594999999998}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-07T12:00:20+00:00","arrival_time":"2026-02-07T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.85478405,"event_time":"2026-02-07T12:00:13+00:00","arrival_time":"2026-02-07T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.85478405,"normal":0.14521594999999998},"reference_distribution":{"anomalous":0.85478405,"normal":0.14521594999999998}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-07T12:00:13+00:00","arrival_time":"2026-02-07T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9439117308986417,"event_time":"2026-02-07T12:00:22+00:00","arrival_time":"2026-02-07T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.85478405,"normal":0.14521594999999998},"reference_distribution":{"anomalous":0.9439117308986417,"normal":0.056088269101358355}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-07T12:00:22+00:00","arrival_time":"2026-02-07T12:00:37+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9439117308986417,"event_time":"2026-02-07T12:00:05+00:00","arrival_time":"2026-02-07T12:00:57+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9439117308986417,"normal":0.056088269101358355},"reference_distribution":{"anomalous":0.9439117308986417,"normal":0.056088269101358355}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-07T12:00:05+00:00","arrival_time":"2026-02-07T12:00:57+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":37,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"8fbd16b98773b16b9ff7811d60058aefdcf87bd344ba35a725e42738ea65c851"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-038","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 038","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-038","label":"Distractor 038","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.88665,"modality":"semantic_status","timestamp":"2026-02-08T12:00:20Z","metadata":{"arrival_time":"2026-02-08T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-038","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.78,"modality":"semantic_status","timestamp":"2026-02-08T12:00:14Z","metadata":{"arrival_time":"2026-02-08T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79532,"modality":"semantic_status","timestamp":"2026-02-08T12:00:22Z","metadata":{"arrival_time":"2026-02-08T12:00:38+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96468,"modality":"semantic_status","timestamp":"2026-02-08T12:00:05Z","metadata":{"arrival_time":"2026-02-08T12:00:58+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-08T12:00:20+00:00","obs-distractor":"2026-02-08T12:00:14+00:00","obs-2":"2026-02-08T12:00:22+00:00","obs-3":"2026-02-08T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-02-08T12:00:10+00:00","obs-distractor":"2026-02-08T12:00:14+00:00","obs-2":"2026-02-08T12:00:38+00:00","obs-3":"2026-02-08T12:00:58+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.926,"edge-ai-1":0.652},"confidence":{"obs-1":0.88665,"obs-distractor":0.78,"obs-2":0.79532,"obs-3":0.96468},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.939202520202059,"event_time":"2026-02-08T12:00:05+00:00","arrival_time":"2026-02-08T12:00:58+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.939202520202059,"normal":0.06079747979794095},"reference_distribution":{"anomalous":0.939202520202059,"normal":0.06079747979794095}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.81898625,"event_time":"2026-02-08T12:00:20+00:00","arrival_time":"2026-02-08T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.81898625,"normal":0.18101374999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-08T12:00:20+00:00","arrival_time":"2026-02-08T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.81898625,"event_time":"2026-02-08T12:00:14+00:00","arrival_time":"2026-02-08T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.81898625,"normal":0.18101374999999997},"reference_distribution":{"anomalous":0.81898625,"normal":0.18101374999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-08T12:00:14+00:00","arrival_time":"2026-02-08T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.939202520202059,"event_time":"2026-02-08T12:00:22+00:00","arrival_time":"2026-02-08T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.81898625,"normal":0.18101374999999997},"reference_distribution":{"anomalous":0.939202520202059,"normal":0.06079747979794095}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-08T12:00:22+00:00","arrival_time":"2026-02-08T12:00:38+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.939202520202059,"event_time":"2026-02-08T12:00:05+00:00","arrival_time":"2026-02-08T12:00:58+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.939202520202059,"normal":0.06079747979794095},"reference_distribution":{"anomalous":0.939202520202059,"normal":0.06079747979794095}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-08T12:00:05+00:00","arrival_time":"2026-02-08T12:00:58+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":38,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"754369b0a9661f5954f258d4ab5eaf1d5d28b1ed2b7e7f13ec3692b2988b7804"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-039","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 039","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-039","label":"Distractor 039","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.886825,"modality":"semantic_status","timestamp":"2026-02-09T12:00:20Z","metadata":{"arrival_time":"2026-02-09T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-039","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.79,"modality":"semantic_status","timestamp":"2026-02-09T12:00:12Z","metadata":{"arrival_time":"2026-02-09T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79546,"modality":"semantic_status","timestamp":"2026-02-09T12:00:22Z","metadata":{"arrival_time":"2026-02-09T12:00:39+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96454,"modality":"semantic_status","timestamp":"2026-02-09T12:00:05Z","metadata":{"arrival_time":"2026-02-09T12:00:59+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-02-09T12:00:20+00:00","obs-distractor":"2026-02-09T12:00:12+00:00","obs-2":"2026-02-09T12:00:22+00:00","obs-3":"2026-02-09T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-02-09T12:00:10+00:00","obs-distractor":"2026-02-09T12:00:12+00:00","obs-2":"2026-02-09T12:00:39+00:00","obs-3":"2026-02-09T12:00:59+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.934,"edge-ai-1":0.52},"confidence":{"obs-1":0.886825,"obs-distractor":0.79,"obs-2":0.79546,"obs-3":0.96454},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9481254940367966,"event_time":"2026-02-09T12:00:05+00:00","arrival_time":"2026-02-09T12:00:59+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9481254940367966,"normal":0.051874505963203484},"reference_distribution":{"anomalous":0.9481254940367966,"normal":0.051874505963203484}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.86129455,"event_time":"2026-02-09T12:00:20+00:00","arrival_time":"2026-02-09T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.86129455,"normal":0.13870545}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-09T12:00:20+00:00","arrival_time":"2026-02-09T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.86129455,"event_time":"2026-02-09T12:00:12+00:00","arrival_time":"2026-02-09T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.86129455,"normal":0.13870545},"reference_distribution":{"anomalous":0.86129455,"normal":0.13870545}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-09T12:00:12+00:00","arrival_time":"2026-02-09T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9481254940367966,"event_time":"2026-02-09T12:00:22+00:00","arrival_time":"2026-02-09T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.86129455,"normal":0.13870545},"reference_distribution":{"anomalous":0.9481254940367966,"normal":0.051874505963203484}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-09T12:00:22+00:00","arrival_time":"2026-02-09T12:00:39+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9481254940367966,"event_time":"2026-02-09T12:00:05+00:00","arrival_time":"2026-02-09T12:00:59+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9481254940367966,"normal":0.051874505963203484},"reference_distribution":{"anomalous":0.9481254940367966,"normal":0.051874505963203484}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-09T12:00:05+00:00","arrival_time":"2026-02-09T12:00:59+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":39,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"6b195832297146d39559d997f886e05e779180ac930b6089de67ba93bd74e6bc"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-040","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 040","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-040","label":"Distractor 040","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.887,"modality":"semantic_status","timestamp":"2026-02-10T12:00:20Z","metadata":{"arrival_time":"2026-02-10T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-040","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-02-10T12:00:13Z","metadata":{"arrival_time":"2026-02-10T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.7956,"modality":"semantic_status","timestamp":"2026-02-10T12:00:22Z","metadata":{"arrival_time":"2026-02-10T12:00:40+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9644,"modality":"semantic_status","timestamp":"2026-02-10T12:00:05Z","metadata":{"arrival_time":"2026-02-10T12:01:00+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-10T12:00:20+00:00","obs-distractor":"2026-02-10T12:00:13+00:00","obs-2":"2026-02-10T12:00:22+00:00","obs-3":"2026-02-10T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-02-10T12:00:10+00:00","obs-distractor":"2026-02-10T12:00:13+00:00","obs-2":"2026-02-10T12:00:40+00:00","obs-3":"2026-02-10T12:01:00+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.942,"edge-ai-1":0.531},"confidence":{"obs-1":0.887,"obs-distractor":0.6,"obs-2":0.7956,"obs-3":0.9644},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9435292112431248,"event_time":"2026-02-10T12:00:05+00:00","arrival_time":"2026-02-10T12:01:00+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9435292112431248,"normal":0.056470788756875244},"reference_distribution":{"anomalous":0.9435292112431248,"normal":0.056470788756875244}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.826241,"event_time":"2026-02-10T12:00:20+00:00","arrival_time":"2026-02-10T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.826241,"normal":0.173759}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-10T12:00:20+00:00","arrival_time":"2026-02-10T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.826241,"event_time":"2026-02-10T12:00:13+00:00","arrival_time":"2026-02-10T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.826241,"normal":0.173759},"reference_distribution":{"anomalous":0.826241,"normal":0.173759}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-10T12:00:13+00:00","arrival_time":"2026-02-10T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9435292112431248,"event_time":"2026-02-10T12:00:22+00:00","arrival_time":"2026-02-10T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.826241,"normal":0.173759},"reference_distribution":{"anomalous":0.9435292112431248,"normal":0.056470788756875244}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-10T12:00:22+00:00","arrival_time":"2026-02-10T12:00:40+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9435292112431248,"event_time":"2026-02-10T12:00:05+00:00","arrival_time":"2026-02-10T12:01:00+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9435292112431248,"normal":0.056470788756875244},"reference_distribution":{"anomalous":0.9435292112431248,"normal":0.056470788756875244}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-10T12:00:05+00:00","arrival_time":"2026-02-10T12:01:00+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":40,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"5c3c5b14d4d1399badd00f589408615eccaeab4b5a1cedae10b701f0ca42fe94"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-041","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 041","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-041","label":"Distractor 041","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.887175,"modality":"semantic_status","timestamp":"2026-02-11T12:00:20Z","metadata":{"arrival_time":"2026-02-11T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-041","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-02-11T12:00:14Z","metadata":{"arrival_time":"2026-02-11T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79574,"modality":"semantic_status","timestamp":"2026-02-11T12:00:22Z","metadata":{"arrival_time":"2026-02-11T12:00:41+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96426,"modality":"semantic_status","timestamp":"2026-02-11T12:00:05Z","metadata":{"arrival_time":"2026-02-11T12:01:01+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-02-11T12:00:20+00:00","obs-distractor":"2026-02-11T12:00:14+00:00","obs-2":"2026-02-11T12:00:22+00:00","obs-3":"2026-02-11T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-02-11T12:00:10+00:00","obs-distractor":"2026-02-11T12:00:14+00:00","obs-2":"2026-02-11T12:00:41+00:00","obs-3":"2026-02-11T12:01:01+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.95,"edge-ai-1":0.542},"confidence":{"obs-1":0.887175,"obs-distractor":0.61,"obs-2":0.79574,"obs-3":0.96426},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.952162975185205,"event_time":"2026-02-11T12:00:05+00:00","arrival_time":"2026-02-11T12:01:01+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.952162975185205,"normal":0.04783702481479498},"reference_distribution":{"anomalous":0.952162975185205,"normal":0.04783702481479498}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.86781625,"event_time":"2026-02-11T12:00:20+00:00","arrival_time":"2026-02-11T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.86781625,"normal":0.13218375000000004}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-11T12:00:20+00:00","arrival_time":"2026-02-11T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.86781625,"event_time":"2026-02-11T12:00:14+00:00","arrival_time":"2026-02-11T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.86781625,"normal":0.13218375000000004},"reference_distribution":{"anomalous":0.86781625,"normal":0.13218375000000004}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-11T12:00:14+00:00","arrival_time":"2026-02-11T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.952162975185205,"event_time":"2026-02-11T12:00:22+00:00","arrival_time":"2026-02-11T12:00:41+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.86781625,"normal":0.13218375000000004},"reference_distribution":{"anomalous":0.952162975185205,"normal":0.04783702481479498}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-11T12:00:22+00:00","arrival_time":"2026-02-11T12:00:41+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.952162975185205,"event_time":"2026-02-11T12:00:05+00:00","arrival_time":"2026-02-11T12:01:01+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.952162975185205,"normal":0.04783702481479498},"reference_distribution":{"anomalous":0.952162975185205,"normal":0.04783702481479498}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-11T12:00:05+00:00","arrival_time":"2026-02-11T12:01:01+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":41,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"4794b61c90a2be3e947dae38af24ea9eaf02901c84854d6351890d375f522e6b"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-042","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 042","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-042","label":"Distractor 042","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.88735,"modality":"semantic_status","timestamp":"2026-02-12T12:00:20Z","metadata":{"arrival_time":"2026-02-12T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-042","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-02-12T12:00:12Z","metadata":{"arrival_time":"2026-02-12T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79588,"modality":"semantic_status","timestamp":"2026-02-12T12:00:22Z","metadata":{"arrival_time":"2026-02-12T12:00:42+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96412,"modality":"semantic_status","timestamp":"2026-02-12T12:00:05Z","metadata":{"arrival_time":"2026-02-12T12:01:02+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-12T12:00:20+00:00","obs-distractor":"2026-02-12T12:00:12+00:00","obs-2":"2026-02-12T12:00:22+00:00","obs-3":"2026-02-12T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-02-12T12:00:10+00:00","obs-distractor":"2026-02-12T12:00:12+00:00","obs-2":"2026-02-12T12:00:42+00:00","obs-3":"2026-02-12T12:01:02+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.958,"edge-ai-1":0.553},"confidence":{"obs-1":0.88735,"obs-distractor":0.62,"obs-2":0.79588,"obs-3":0.96412},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9476782185336842,"event_time":"2026-02-12T12:00:05+00:00","arrival_time":"2026-02-12T12:01:02+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9476782185336842,"normal":0.05232178146631587},"reference_distribution":{"anomalous":0.9476782185336842,"normal":0.05232178146631587}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.83350835,"event_time":"2026-02-12T12:00:20+00:00","arrival_time":"2026-02-12T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.83350835,"normal":0.16649165}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-12T12:00:20+00:00","arrival_time":"2026-02-12T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.83350835,"event_time":"2026-02-12T12:00:12+00:00","arrival_time":"2026-02-12T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.83350835,"normal":0.16649165},"reference_distribution":{"anomalous":0.83350835,"normal":0.16649165}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-12T12:00:12+00:00","arrival_time":"2026-02-12T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9476782185336842,"event_time":"2026-02-12T12:00:22+00:00","arrival_time":"2026-02-12T12:00:42+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.83350835,"normal":0.16649165},"reference_distribution":{"anomalous":0.9476782185336842,"normal":0.05232178146631587}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-12T12:00:22+00:00","arrival_time":"2026-02-12T12:00:42+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9476782185336842,"event_time":"2026-02-12T12:00:05+00:00","arrival_time":"2026-02-12T12:01:02+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9476782185336842,"normal":0.05232178146631587},"reference_distribution":{"anomalous":0.9476782185336842,"normal":0.05232178146631587}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-12T12:00:05+00:00","arrival_time":"2026-02-12T12:01:02+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":42,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"2fe1dfd404847fff182027d8d74d853979453fd33da5bc839749d74b7d7a9d99"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-043","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 043","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-043","label":"Distractor 043","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.887525,"modality":"semantic_status","timestamp":"2026-02-13T12:00:20Z","metadata":{"arrival_time":"2026-02-13T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79602,"modality":"semantic_status","timestamp":"2026-02-13T12:00:22Z","metadata":{"arrival_time":"2026-02-13T12:00:43+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96398,"modality":"semantic_status","timestamp":"2026-02-13T12:00:05Z","metadata":{"arrival_time":"2026-02-13T12:01:03+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-043","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-02-13T12:00:13Z","metadata":{"arrival_time":"2026-02-13T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-13T12:00:20+00:00","obs-2":"2026-02-13T12:00:22+00:00","obs-3":"2026-02-13T12:00:05+00:00","obs-distractor":"2026-02-13T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-13T12:00:10+00:00","obs-2":"2026-02-13T12:00:43+00:00","obs-3":"2026-02-13T12:01:03+00:00","obs-distractor":"2026-02-13T12:00:13+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.966,"edge-ai-1":0.564},"confidence":{"obs-1":0.887525,"obs-2":0.79602,"obs-3":0.96398,"obs-distractor":0.63},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9560264889460881,"event_time":"2026-02-13T12:00:05+00:00","arrival_time":"2026-02-13T12:01:03+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9560264889460881,"normal":0.04397351105391185},"reference_distribution":{"anomalous":0.9560264889460881,"normal":0.04397351105391185}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.87434915,"event_time":"2026-02-13T12:00:20+00:00","arrival_time":"2026-02-13T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.87434915,"normal":0.12565084999999998}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-13T12:00:20+00:00","arrival_time":"2026-02-13T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.87434915,"event_time":"2026-02-13T12:00:13+00:00","arrival_time":"2026-02-13T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.87434915,"normal":0.12565084999999998},"reference_distribution":{"anomalous":0.87434915,"normal":0.12565084999999998}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-13T12:00:13+00:00","arrival_time":"2026-02-13T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9560264889460881,"event_time":"2026-02-13T12:00:22+00:00","arrival_time":"2026-02-13T12:00:43+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.87434915,"normal":0.12565084999999998},"reference_distribution":{"anomalous":0.9560264889460881,"normal":0.04397351105391185}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-13T12:00:22+00:00","arrival_time":"2026-02-13T12:00:43+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9560264889460881,"event_time":"2026-02-13T12:00:05+00:00","arrival_time":"2026-02-13T12:01:03+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9560264889460881,"normal":0.04397351105391185},"reference_distribution":{"anomalous":0.9560264889460881,"normal":0.04397351105391185}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-13T12:00:05+00:00","arrival_time":"2026-02-13T12:01:03+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":43,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"7e70121832f0e084f4c99121946b8e25ad982bc99a6525f8bedb43075605ec50"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-044","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 044","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-044","label":"Distractor 044","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8877,"modality":"semantic_status","timestamp":"2026-02-14T12:00:20Z","metadata":{"arrival_time":"2026-02-14T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-044","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-02-14T12:00:14Z","metadata":{"arrival_time":"2026-02-14T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79616,"modality":"semantic_status","timestamp":"2026-02-14T12:00:22Z","metadata":{"arrival_time":"2026-02-14T12:00:44+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96384,"modality":"semantic_status","timestamp":"2026-02-14T12:00:05Z","metadata":{"arrival_time":"2026-02-14T12:01:04+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-14T12:00:20+00:00","obs-distractor":"2026-02-14T12:00:14+00:00","obs-2":"2026-02-14T12:00:22+00:00","obs-3":"2026-02-14T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-02-14T12:00:10+00:00","obs-distractor":"2026-02-14T12:00:14+00:00","obs-2":"2026-02-14T12:00:44+00:00","obs-3":"2026-02-14T12:01:04+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.974,"edge-ai-1":0.575},"confidence":{"obs-1":0.8877,"obs-distractor":0.64,"obs-2":0.79616,"obs-3":0.96384},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9380262429665336,"event_time":"2026-02-14T12:00:05+00:00","arrival_time":"2026-02-14T12:01:04+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9380262429665336,"normal":0.061973757033466435},"reference_distribution":{"anomalous":0.9380262429665336,"normal":0.061973757033466435}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8024060000000001,"event_time":"2026-02-14T12:00:20+00:00","arrival_time":"2026-02-14T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8024060000000001,"normal":0.19759399999999994}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-14T12:00:20+00:00","arrival_time":"2026-02-14T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8024060000000001,"event_time":"2026-02-14T12:00:14+00:00","arrival_time":"2026-02-14T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8024060000000001,"normal":0.19759399999999994},"reference_distribution":{"anomalous":0.8024060000000001,"normal":0.19759399999999994}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-14T12:00:14+00:00","arrival_time":"2026-02-14T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9380262429665336,"event_time":"2026-02-14T12:00:22+00:00","arrival_time":"2026-02-14T12:00:44+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8024060000000001,"normal":0.19759399999999994},"reference_distribution":{"anomalous":0.9380262429665336,"normal":0.061973757033466435}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-14T12:00:22+00:00","arrival_time":"2026-02-14T12:00:44+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9380262429665336,"event_time":"2026-02-14T12:00:05+00:00","arrival_time":"2026-02-14T12:01:04+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9380262429665336,"normal":0.061973757033466435},"reference_distribution":{"anomalous":0.9380262429665336,"normal":0.061973757033466435}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-14T12:00:05+00:00","arrival_time":"2026-02-14T12:01:04+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":44,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"9e0b99d62fdb6fbd33dda48a44bdf2c52b440e3cdc46f83d8b47a402ffbadf3b"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-045","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 045","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-045","label":"Distractor 045","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.887875,"modality":"semantic_status","timestamp":"2026-02-15T12:00:20Z","metadata":{"arrival_time":"2026-02-15T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.7963,"modality":"semantic_status","timestamp":"2026-02-15T12:00:22Z","metadata":{"arrival_time":"2026-02-15T12:00:45+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.9637,"modality":"semantic_status","timestamp":"2026-02-15T12:00:05Z","metadata":{"arrival_time":"2026-02-15T12:01:05+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-045","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-02-15T12:00:12Z","metadata":{"arrival_time":"2026-02-15T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-15T12:00:20+00:00","obs-2":"2026-02-15T12:00:22+00:00","obs-3":"2026-02-15T12:00:05+00:00","obs-distractor":"2026-02-15T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-15T12:00:10+00:00","obs-2":"2026-02-15T12:00:45+00:00","obs-3":"2026-02-15T12:01:05+00:00","obs-distractor":"2026-02-15T12:00:12+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.91,"edge-ai-1":0.586},"confidence":{"obs-1":0.887875,"obs-2":0.7963,"obs-3":0.9637,"obs-distractor":0.65},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9411409677252792,"event_time":"2026-02-15T12:00:05+00:00","arrival_time":"2026-02-15T12:01:05+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9411409677252792,"normal":0.058859032274720856},"reference_distribution":{"anomalous":0.9411409677252792,"normal":0.058859032274720856}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8529662499999999,"event_time":"2026-02-15T12:00:20+00:00","arrival_time":"2026-02-15T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8529662499999999,"normal":0.14703375000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-15T12:00:20+00:00","arrival_time":"2026-02-15T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8529662499999999,"event_time":"2026-02-15T12:00:12+00:00","arrival_time":"2026-02-15T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8529662499999999,"normal":0.14703375000000007},"reference_distribution":{"anomalous":0.8529662499999999,"normal":0.14703375000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-15T12:00:12+00:00","arrival_time":"2026-02-15T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9411409677252792,"event_time":"2026-02-15T12:00:22+00:00","arrival_time":"2026-02-15T12:00:45+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8529662499999999,"normal":0.14703375000000007},"reference_distribution":{"anomalous":0.9411409677252792,"normal":0.058859032274720856}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-15T12:00:22+00:00","arrival_time":"2026-02-15T12:00:45+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9411409677252792,"event_time":"2026-02-15T12:00:05+00:00","arrival_time":"2026-02-15T12:01:05+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9411409677252792,"normal":0.058859032274720856},"reference_distribution":{"anomalous":0.9411409677252792,"normal":0.058859032274720856}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-15T12:00:05+00:00","arrival_time":"2026-02-15T12:01:05+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":45,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"f5304fcdc59035330cc4a8481cf3e0bf764fe0ce11e2cddad61aaa495b58ef2e"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-046","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 046","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-046","label":"Distractor 046","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.88805,"modality":"semantic_status","timestamp":"2026-02-16T12:00:20Z","metadata":{"arrival_time":"2026-02-16T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-046","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-02-16T12:00:13Z","metadata":{"arrival_time":"2026-02-16T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79644,"modality":"semantic_status","timestamp":"2026-02-16T12:00:22Z","metadata":{"arrival_time":"2026-02-16T12:00:46+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96356,"modality":"semantic_status","timestamp":"2026-02-16T12:00:05Z","metadata":{"arrival_time":"2026-02-16T12:01:06+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-16T12:00:20+00:00","obs-distractor":"2026-02-16T12:00:13+00:00","obs-2":"2026-02-16T12:00:22+00:00","obs-3":"2026-02-16T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-02-16T12:00:10+00:00","obs-distractor":"2026-02-16T12:00:13+00:00","obs-2":"2026-02-16T12:00:46+00:00","obs-3":"2026-02-16T12:01:06+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.918,"edge-ai-1":0.597},"confidence":{"obs-1":0.88805,"obs-distractor":0.66,"obs-2":0.79644,"obs-3":0.96356},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9351249059088597,"event_time":"2026-02-16T12:00:05+00:00","arrival_time":"2026-02-16T12:01:06+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9351249059088597,"normal":0.06487509409114021},"reference_distribution":{"anomalous":0.9351249059088597,"normal":0.06487509409114021}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8096639000000001,"event_time":"2026-02-16T12:00:20+00:00","arrival_time":"2026-02-16T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8096639000000001,"normal":0.1903360999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-16T12:00:20+00:00","arrival_time":"2026-02-16T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8096639000000001,"event_time":"2026-02-16T12:00:13+00:00","arrival_time":"2026-02-16T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8096639000000001,"normal":0.1903360999999999},"reference_distribution":{"anomalous":0.8096639000000001,"normal":0.1903360999999999}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-16T12:00:13+00:00","arrival_time":"2026-02-16T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9351249059088597,"event_time":"2026-02-16T12:00:22+00:00","arrival_time":"2026-02-16T12:00:46+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8096639000000001,"normal":0.1903360999999999},"reference_distribution":{"anomalous":0.9351249059088597,"normal":0.06487509409114021}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-16T12:00:22+00:00","arrival_time":"2026-02-16T12:00:46+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9351249059088597,"event_time":"2026-02-16T12:00:05+00:00","arrival_time":"2026-02-16T12:01:06+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9351249059088597,"normal":0.06487509409114021},"reference_distribution":{"anomalous":0.9351249059088597,"normal":0.06487509409114021}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-16T12:00:05+00:00","arrival_time":"2026-02-16T12:01:06+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":46,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"aded09c0c05ae3b504a36d4c889fc4bc31506b05ab84962878fa958fb1f129ee"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-047","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 047","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-047","label":"Distractor 047","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.888225,"modality":"semantic_status","timestamp":"2026-02-17T12:00:20Z","metadata":{"arrival_time":"2026-02-17T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79658,"modality":"semantic_status","timestamp":"2026-02-17T12:00:22Z","metadata":{"arrival_time":"2026-02-17T12:00:47+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96342,"modality":"semantic_status","timestamp":"2026-02-17T12:00:05Z","metadata":{"arrival_time":"2026-02-17T12:01:07+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-047","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-02-17T12:00:14Z","metadata":{"arrival_time":"2026-02-17T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-2":"robot-1","obs-3":"robot-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-17T12:00:20+00:00","obs-2":"2026-02-17T12:00:22+00:00","obs-3":"2026-02-17T12:00:05+00:00","obs-distractor":"2026-02-17T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-17T12:00:10+00:00","obs-2":"2026-02-17T12:00:47+00:00","obs-3":"2026-02-17T12:01:07+00:00","obs-distractor":"2026-02-17T12:00:14+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.926,"edge-ai-1":0.608},"confidence":{"obs-1":0.888225,"obs-2":0.79658,"obs-3":0.96342,"obs-distractor":0.67},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9455072784394248,"event_time":"2026-02-17T12:00:05+00:00","arrival_time":"2026-02-17T12:01:07+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9455072784394248,"normal":0.05449272156057515},"reference_distribution":{"anomalous":0.9455072784394248,"normal":0.05449272156057515}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.8594963500000001,"event_time":"2026-02-17T12:00:20+00:00","arrival_time":"2026-02-17T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8594963500000001,"normal":0.14050364999999987}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-17T12:00:20+00:00","arrival_time":"2026-02-17T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8594963500000001,"event_time":"2026-02-17T12:00:14+00:00","arrival_time":"2026-02-17T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8594963500000001,"normal":0.14050364999999987},"reference_distribution":{"anomalous":0.8594963500000001,"normal":0.14050364999999987}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-17T12:00:14+00:00","arrival_time":"2026-02-17T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9455072784394248,"event_time":"2026-02-17T12:00:22+00:00","arrival_time":"2026-02-17T12:00:47+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8594963500000001,"normal":0.14050364999999987},"reference_distribution":{"anomalous":0.9455072784394248,"normal":0.05449272156057515}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-17T12:00:22+00:00","arrival_time":"2026-02-17T12:00:47+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9455072784394248,"event_time":"2026-02-17T12:00:05+00:00","arrival_time":"2026-02-17T12:01:07+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9455072784394248,"normal":0.05449272156057515},"reference_distribution":{"anomalous":0.9455072784394248,"normal":0.05449272156057515}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-17T12:00:05+00:00","arrival_time":"2026-02-17T12:01:07+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":47,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"ab5edb60b5647d821f4761750921fd2bc3d6e957e6cd5b4e057c189b2db75deb"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-048","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 048","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-048","label":"Distractor 048","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8884,"modality":"semantic_status","timestamp":"2026-02-18T12:00:20Z","metadata":{"arrival_time":"2026-02-18T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79672,"modality":"semantic_status","timestamp":"2026-02-18T12:00:22Z","metadata":{"arrival_time":"2026-02-18T12:00:48+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96328,"modality":"semantic_status","timestamp":"2026-02-18T12:00:05Z","metadata":{"arrival_time":"2026-02-18T12:01:08+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-048","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-02-18T12:00:12Z","metadata":{"arrival_time":"2026-02-18T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"robot-1","obs-2":"iot-sensor-1","obs-3":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-18T12:00:20+00:00","obs-2":"2026-02-18T12:00:22+00:00","obs-3":"2026-02-18T12:00:05+00:00","obs-distractor":"2026-02-18T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-18T12:00:10+00:00","obs-2":"2026-02-18T12:00:48+00:00","obs-3":"2026-02-18T12:01:08+00:00","obs-distractor":"2026-02-18T12:00:12+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.934,"edge-ai-1":0.619},"confidence":{"obs-1":0.8884,"obs-2":0.79672,"obs-3":0.96328,"obs-distractor":0.68},"state_epochs":{"obs-1":2,"obs-2":2,"obs-3":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9396173359374874,"event_time":"2026-02-18T12:00:05+00:00","arrival_time":"2026-02-18T12:01:08+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9396173359374874,"normal":0.060382664062512525},"reference_distribution":{"anomalous":0.9396173359374874,"normal":0.060382664062512525}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.8169344,"event_time":"2026-02-18T12:00:20+00:00","arrival_time":"2026-02-18T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.8169344,"normal":0.18306560000000005}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-18T12:00:20+00:00","arrival_time":"2026-02-18T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.8169344,"event_time":"2026-02-18T12:00:12+00:00","arrival_time":"2026-02-18T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8169344,"normal":0.18306560000000005},"reference_distribution":{"anomalous":0.8169344,"normal":0.18306560000000005}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-18T12:00:12+00:00","arrival_time":"2026-02-18T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9396173359374874,"event_time":"2026-02-18T12:00:22+00:00","arrival_time":"2026-02-18T12:00:48+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.8169344,"normal":0.18306560000000005},"reference_distribution":{"anomalous":0.9396173359374874,"normal":0.060382664062512525}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-18T12:00:22+00:00","arrival_time":"2026-02-18T12:00:48+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.9396173359374874,"event_time":"2026-02-18T12:00:05+00:00","arrival_time":"2026-02-18T12:01:08+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9396173359374874,"normal":0.060382664062512525},"reference_distribution":{"anomalous":0.9396173359374874,"normal":0.060382664062512525}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-18T12:00:05+00:00","arrival_time":"2026-02-18T12:01:08+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":48,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"d29710f6ee52918f88b385122107ffff5d3f26125142402c293b2c135710f22e"}}
{"id":"evaluation-v1-stale_delayed_evidence-20260725-049","name":"Evaluation v1.0 trajectory: stale_delayed_evidence case 049","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-049","label":"Distractor 049","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.888575,"modality":"semantic_status","timestamp":"2026-02-19T12:00:20Z","metadata":{"arrival_time":"2026-02-19T12:00:10+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-049","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-02-19T12:00:13Z","metadata":{"arrival_time":"2026-02-19T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.79686,"modality":"semantic_status","timestamp":"2026-02-19T12:00:22Z","metadata":{"arrival_time":"2026-02-19T12:00:49+00:00","state_epoch":2,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-3","agent_id":"robot-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.96314,"modality":"semantic_status","timestamp":"2026-02-19T12:00:05Z","metadata":{"arrival_time":"2026-02-19T12:01:09+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"anomalous"}},"contradictions":[],"next_action":{"action_type":"inspect","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"iot-sensor-1","obs-distractor":"edge-ai-1","obs-2":"robot-1","obs-3":"robot-1"},"event_times":{"obs-1":"2026-02-19T12:00:20+00:00","obs-distractor":"2026-02-19T12:00:13+00:00","obs-2":"2026-02-19T12:00:22+00:00","obs-3":"2026-02-19T12:00:05+00:00"},"arrival_times":{"obs-1":"2026-02-19T12:00:10+00:00","obs-distractor":"2026-02-19T12:00:13+00:00","obs-2":"2026-02-19T12:00:49+00:00","obs-3":"2026-02-19T12:01:09+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.942,"edge-ai-1":0.63},"confidence":{"obs-1":0.888575,"obs-distractor":0.69,"obs-2":0.79686,"obs-3":0.96314},"state_epochs":{"obs-1":2,"obs-distractor":1,"obs-2":2,"obs-3":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9496939269143262,"event_time":"2026-02-19T12:00:05+00:00","arrival_time":"2026-02-19T12:01:09+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9496939269143262,"normal":0.05030607308567373},"reference_distribution":{"anomalous":0.9496939269143262,"normal":0.05030607308567373}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"iot-sensor-1","reference_confidence":0.86603765,"event_time":"2026-02-19T12:00:20+00:00","arrival_time":"2026-02-19T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.86603765,"normal":0.13396235}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-19T12:00:20+00:00","arrival_time":"2026-02-19T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.86603765,"event_time":"2026-02-19T12:00:13+00:00","arrival_time":"2026-02-19T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.86603765,"normal":0.13396235},"reference_distribution":{"anomalous":0.86603765,"normal":0.13396235}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-19T12:00:13+00:00","arrival_time":"2026-02-19T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"strengthened","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9496939269143262,"event_time":"2026-02-19T12:00:22+00:00","arrival_time":"2026-02-19T12:00:49+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.86603765,"normal":0.13396235},"reference_distribution":{"anomalous":0.9496939269143262,"normal":0.05030607308567373}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":"2026-02-19T12:00:22+00:00","arrival_time":"2026-02-19T12:00:49+00:00"},{"step_index":4,"new_evidence_ids":["obs-3"],"available_evidence_ids":["obs-1","obs-distractor","obs-2","obs-3"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":["obs-3"],"superseded_evidence_ids":[],"event_types":["stale_evidence","preserve"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1","obs-2"],"contradicting_evidence":[],"provenance":"robot-1","reference_confidence":0.9496939269143262,"event_time":"2026-02-19T12:00:05+00:00","arrival_time":"2026-02-19T12:01:09+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.9496939269143262,"normal":0.05030607308567373},"reference_distribution":{"anomalous":0.9496939269143262,"normal":0.05030607308567373}}],"contradictions":[{"contradiction_id":"evaluation-v1-stale_delayed_evidence-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"stale_or_superseded_claims_excluded","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-19T12:00:05+00:00","arrival_time":"2026-02-19T12:01:09+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"stale_delayed_evidence","case_index":49,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"5a6713cdc2ff5c8f362795f9ff41fc1edc32c4017bf66ec67833d83a6e9b78a4"}}
{"id":"evaluation-v1-source_reliability-20260725-000","name":"Evaluation v1.0 trajectory: source_reliability case 000","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-000","label":"Distractor 000","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87,"modality":"semantic_status","timestamp":"2026-01-01T12:00:10Z","metadata":{"arrival_time":"2026-01-01T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-000","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-01-01T12:00:12Z","metadata":{"arrival_time":"2026-01-01T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87,"modality":"semantic_status","timestamp":"2026-01-01T12:00:20Z","metadata":{"arrival_time":"2026-01-01T12:00:24+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-01T12:00:10+00:00","obs-distractor":"2026-01-01T12:00:12+00:00","obs-2":"2026-01-01T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-01T12:00:10+00:00","obs-distractor":"2026-01-01T12:00:12+00:00","obs-2":"2026-01-01T12:00:24+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.91,"edge-ai-1":0.52},"confidence":{"obs-1":0.87,"obs-distractor":0.6,"obs-2":0.87},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-000-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6947695192262215,"event_time":"2026-01-01T12:00:20+00:00","arrival_time":"2026-01-01T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6924,"normal":0.3076},"reference_distribution":{"anomalous":0.3052304807737784,"normal":0.6947695192262215}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.6924,"event_time":"2026-01-01T12:00:10+00:00","arrival_time":"2026-01-01T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.6924,"normal":0.3076}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-01T12:00:10+00:00","arrival_time":"2026-01-01T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.6924,"event_time":"2026-01-01T12:00:12+00:00","arrival_time":"2026-01-01T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6924,"normal":0.3076},"reference_distribution":{"anomalous":0.6924,"normal":0.3076}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-000-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-01T12:00:12+00:00","arrival_time":"2026-01-01T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6947695192262215,"event_time":"2026-01-01T12:00:20+00:00","arrival_time":"2026-01-01T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6924,"normal":0.3076},"reference_distribution":{"anomalous":0.3052304807737784,"normal":0.6947695192262215}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-000-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-01T12:00:20+00:00","arrival_time":"2026-01-01T12:00:24+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":0,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"28411c57af007b41675576652206187f41ea77ef137520d82045d4cdb7c8bc9b"}}
{"id":"evaluation-v1-source_reliability-20260725-001","name":"Evaluation v1.0 trajectory: source_reliability case 001","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-001","label":"Distractor 001","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87014,"modality":"semantic_status","timestamp":"2026-01-02T12:00:10Z","metadata":{"arrival_time":"2026-01-02T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-001","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-01-02T12:00:13Z","metadata":{"arrival_time":"2026-01-02T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87014,"modality":"semantic_status","timestamp":"2026-01-02T12:00:20Z","metadata":{"arrival_time":"2026-01-02T12:00:25+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-02T12:00:10+00:00","obs-distractor":"2026-01-02T12:00:13+00:00","obs-2":"2026-01-02T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-02T12:00:10+00:00","obs-distractor":"2026-01-02T12:00:13+00:00","obs-2":"2026-01-02T12:00:25+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.918,"edge-ai-1":0.531},"confidence":{"obs-1":0.87014,"obs-distractor":0.61,"obs-2":0.87014},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-001-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6954575435800832,"event_time":"2026-01-02T12:00:20+00:00","arrival_time":"2026-01-02T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.69654434,"normal":0.30345566},"reference_distribution":{"anomalous":0.30454245641991684,"normal":0.6954575435800832}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.69654434,"event_time":"2026-01-02T12:00:10+00:00","arrival_time":"2026-01-02T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.69654434,"normal":0.30345566}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-02T12:00:10+00:00","arrival_time":"2026-01-02T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.69654434,"event_time":"2026-01-02T12:00:13+00:00","arrival_time":"2026-01-02T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.69654434,"normal":0.30345566},"reference_distribution":{"anomalous":0.69654434,"normal":0.30345566}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-001-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-02T12:00:13+00:00","arrival_time":"2026-01-02T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6954575435800832,"event_time":"2026-01-02T12:00:20+00:00","arrival_time":"2026-01-02T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.69654434,"normal":0.30345566},"reference_distribution":{"anomalous":0.30454245641991684,"normal":0.6954575435800832}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-001-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-02T12:00:20+00:00","arrival_time":"2026-01-02T12:00:25+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":1,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"d298ac860f26fe0cf3e0d287401b8db5053304fe83dbe6fc19df4949552b815f"}}
{"id":"evaluation-v1-source_reliability-20260725-002","name":"Evaluation v1.0 trajectory: source_reliability case 002","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-002","label":"Distractor 002","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87028,"modality":"semantic_status","timestamp":"2026-01-03T12:00:10Z","metadata":{"arrival_time":"2026-01-03T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-002","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-01-03T12:00:14Z","metadata":{"arrival_time":"2026-01-03T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87028,"modality":"semantic_status","timestamp":"2026-01-03T12:00:20Z","metadata":{"arrival_time":"2026-01-03T12:00:26+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-03T12:00:10+00:00","obs-distractor":"2026-01-03T12:00:14+00:00","obs-2":"2026-01-03T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-03T12:00:10+00:00","obs-distractor":"2026-01-03T12:00:14+00:00","obs-2":"2026-01-03T12:00:26+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.926,"edge-ai-1":0.542},"confidence":{"obs-1":0.87028,"obs-distractor":0.62,"obs-2":0.87028},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-002-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.696188959793959,"event_time":"2026-01-03T12:00:20+00:00","arrival_time":"2026-01-03T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70069176,"normal":0.29930824},"reference_distribution":{"anomalous":0.30381104020604105,"normal":0.696188959793959}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.70069176,"event_time":"2026-01-03T12:00:10+00:00","arrival_time":"2026-01-03T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.70069176,"normal":0.29930824}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-03T12:00:10+00:00","arrival_time":"2026-01-03T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.70069176,"event_time":"2026-01-03T12:00:14+00:00","arrival_time":"2026-01-03T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70069176,"normal":0.29930824},"reference_distribution":{"anomalous":0.70069176,"normal":0.29930824}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-002-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-03T12:00:14+00:00","arrival_time":"2026-01-03T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.696188959793959,"event_time":"2026-01-03T12:00:20+00:00","arrival_time":"2026-01-03T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70069176,"normal":0.29930824},"reference_distribution":{"anomalous":0.30381104020604105,"normal":0.696188959793959}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-002-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-03T12:00:20+00:00","arrival_time":"2026-01-03T12:00:26+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":2,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"b8e82e4a676d2d4505d5d5bbf5199694a8a8855def6d62c67a1e1a8ec8754a33"}}
{"id":"evaluation-v1-source_reliability-20260725-003","name":"Evaluation v1.0 trajectory: source_reliability case 003","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-003","label":"Distractor 003","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87042,"modality":"semantic_status","timestamp":"2026-01-04T12:00:10Z","metadata":{"arrival_time":"2026-01-04T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-003","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-01-04T12:00:12Z","metadata":{"arrival_time":"2026-01-04T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87042,"modality":"semantic_status","timestamp":"2026-01-04T12:00:20Z","metadata":{"arrival_time":"2026-01-04T12:00:27+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-04T12:00:10+00:00","obs-distractor":"2026-01-04T12:00:12+00:00","obs-2":"2026-01-04T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-04T12:00:10+00:00","obs-distractor":"2026-01-04T12:00:12+00:00","obs-2":"2026-01-04T12:00:27+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.934,"edge-ai-1":0.553},"confidence":{"obs-1":0.87042,"obs-distractor":0.63,"obs-2":0.87042},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-003-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6969656368230842,"event_time":"2026-01-04T12:00:20+00:00","arrival_time":"2026-01-04T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7048422599999999,"normal":0.29515774000000006},"reference_distribution":{"anomalous":0.30303436317691573,"normal":0.6969656368230842}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7048422599999999,"event_time":"2026-01-04T12:00:10+00:00","arrival_time":"2026-01-04T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.7048422599999999,"normal":0.29515774000000006}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-04T12:00:10+00:00","arrival_time":"2026-01-04T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7048422599999999,"event_time":"2026-01-04T12:00:12+00:00","arrival_time":"2026-01-04T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7048422599999999,"normal":0.29515774000000006},"reference_distribution":{"anomalous":0.7048422599999999,"normal":0.29515774000000006}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-003-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-04T12:00:12+00:00","arrival_time":"2026-01-04T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6969656368230842,"event_time":"2026-01-04T12:00:20+00:00","arrival_time":"2026-01-04T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7048422599999999,"normal":0.29515774000000006},"reference_distribution":{"anomalous":0.30303436317691573,"normal":0.6969656368230842}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-003-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-04T12:00:20+00:00","arrival_time":"2026-01-04T12:00:27+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":3,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"4af7e5af88bb930c7d8e9baba4b8cfdf74c581790aa87434b4e8033a43f8a9bd"}}
{"id":"evaluation-v1-source_reliability-20260725-004","name":"Evaluation v1.0 trajectory: source_reliability case 004","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-004","label":"Distractor 004","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87056,"modality":"semantic_status","timestamp":"2026-01-05T12:00:10Z","metadata":{"arrival_time":"2026-01-05T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-004","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-01-05T12:00:13Z","metadata":{"arrival_time":"2026-01-05T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87056,"modality":"semantic_status","timestamp":"2026-01-05T12:00:20Z","metadata":{"arrival_time":"2026-01-05T12:00:28+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-05T12:00:10+00:00","obs-distractor":"2026-01-05T12:00:13+00:00","obs-2":"2026-01-05T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-05T12:00:10+00:00","obs-distractor":"2026-01-05T12:00:13+00:00","obs-2":"2026-01-05T12:00:28+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.942,"edge-ai-1":0.564},"confidence":{"obs-1":0.87056,"obs-distractor":0.64,"obs-2":0.87056},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-004-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6977895725650013,"event_time":"2026-01-05T12:00:20+00:00","arrival_time":"2026-01-05T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70899584,"normal":0.29100415999999996},"reference_distribution":{"anomalous":0.30221042743499876,"normal":0.6977895725650013}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.70899584,"event_time":"2026-01-05T12:00:10+00:00","arrival_time":"2026-01-05T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.70899584,"normal":0.29100415999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-05T12:00:10+00:00","arrival_time":"2026-01-05T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.70899584,"event_time":"2026-01-05T12:00:13+00:00","arrival_time":"2026-01-05T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70899584,"normal":0.29100415999999996},"reference_distribution":{"anomalous":0.70899584,"normal":0.29100415999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-004-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-05T12:00:13+00:00","arrival_time":"2026-01-05T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6977895725650013,"event_time":"2026-01-05T12:00:20+00:00","arrival_time":"2026-01-05T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70899584,"normal":0.29100415999999996},"reference_distribution":{"anomalous":0.30221042743499876,"normal":0.6977895725650013}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-004-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-05T12:00:20+00:00","arrival_time":"2026-01-05T12:00:28+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":4,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"0b1026ec4a0f8d97061c0d247633731aa8d6516fc326bc1aafcaaf69b834c6d7"}}
{"id":"evaluation-v1-source_reliability-20260725-005","name":"Evaluation v1.0 trajectory: source_reliability case 005","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-005","label":"Distractor 005","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8707,"modality":"semantic_status","timestamp":"2026-01-06T12:00:10Z","metadata":{"arrival_time":"2026-01-06T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-005","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-01-06T12:00:14Z","metadata":{"arrival_time":"2026-01-06T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8707,"modality":"semantic_status","timestamp":"2026-01-06T12:00:20Z","metadata":{"arrival_time":"2026-01-06T12:00:29+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-06T12:00:10+00:00","obs-distractor":"2026-01-06T12:00:14+00:00","obs-2":"2026-01-06T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-06T12:00:10+00:00","obs-distractor":"2026-01-06T12:00:14+00:00","obs-2":"2026-01-06T12:00:29+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.95,"edge-ai-1":0.575},"confidence":{"obs-1":0.8707,"obs-distractor":0.65,"obs-2":0.8707},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-005-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6986629046951556,"event_time":"2026-01-06T12:00:20+00:00","arrival_time":"2026-01-06T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7131525,"normal":0.28684750000000003},"reference_distribution":{"anomalous":0.3013370953048444,"normal":0.6986629046951556}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7131525,"event_time":"2026-01-06T12:00:10+00:00","arrival_time":"2026-01-06T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.7131525,"normal":0.28684750000000003}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-06T12:00:10+00:00","arrival_time":"2026-01-06T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7131525,"event_time":"2026-01-06T12:00:14+00:00","arrival_time":"2026-01-06T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7131525,"normal":0.28684750000000003},"reference_distribution":{"anomalous":0.7131525,"normal":0.28684750000000003}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-005-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-06T12:00:14+00:00","arrival_time":"2026-01-06T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6986629046951556,"event_time":"2026-01-06T12:00:20+00:00","arrival_time":"2026-01-06T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7131525,"normal":0.28684750000000003},"reference_distribution":{"anomalous":0.3013370953048444,"normal":0.6986629046951556}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-005-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-06T12:00:20+00:00","arrival_time":"2026-01-06T12:00:29+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":5,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"fedc00f493e397d1c7a610df880d9092eb5a71e6b035190bdf0547b08e2da972"}}
{"id":"evaluation-v1-source_reliability-20260725-006","name":"Evaluation v1.0 trajectory: source_reliability case 006","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-006","label":"Distractor 006","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87084,"modality":"semantic_status","timestamp":"2026-01-07T12:00:10Z","metadata":{"arrival_time":"2026-01-07T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-006","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-01-07T12:00:12Z","metadata":{"arrival_time":"2026-01-07T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87084,"modality":"semantic_status","timestamp":"2026-01-07T12:00:20Z","metadata":{"arrival_time":"2026-01-07T12:00:30+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-07T12:00:10+00:00","obs-distractor":"2026-01-07T12:00:12+00:00","obs-2":"2026-01-07T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-07T12:00:10+00:00","obs-distractor":"2026-01-07T12:00:12+00:00","obs-2":"2026-01-07T12:00:30+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.958,"edge-ai-1":0.586},"confidence":{"obs-1":0.87084,"obs-distractor":0.66,"obs-2":0.87084},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-006-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.699587922625405,"event_time":"2026-01-07T12:00:20+00:00","arrival_time":"2026-01-07T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7173122399999999,"normal":0.28268776000000007},"reference_distribution":{"anomalous":0.30041207737459497,"normal":0.699587922625405}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7173122399999999,"event_time":"2026-01-07T12:00:10+00:00","arrival_time":"2026-01-07T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.7173122399999999,"normal":0.28268776000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-07T12:00:10+00:00","arrival_time":"2026-01-07T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7173122399999999,"event_time":"2026-01-07T12:00:12+00:00","arrival_time":"2026-01-07T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7173122399999999,"normal":0.28268776000000007},"reference_distribution":{"anomalous":0.7173122399999999,"normal":0.28268776000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-006-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-07T12:00:12+00:00","arrival_time":"2026-01-07T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.699587922625405,"event_time":"2026-01-07T12:00:20+00:00","arrival_time":"2026-01-07T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7173122399999999,"normal":0.28268776000000007},"reference_distribution":{"anomalous":0.30041207737459497,"normal":0.699587922625405}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-006-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-07T12:00:20+00:00","arrival_time":"2026-01-07T12:00:30+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":6,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"6cf52708626db11d5a0f8cdf2c068b7e1758c61d487203b3f597b00e4864ae1e"}}
{"id":"evaluation-v1-source_reliability-20260725-007","name":"Evaluation v1.0 trajectory: source_reliability case 007","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-007","label":"Distractor 007","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87098,"modality":"semantic_status","timestamp":"2026-01-08T12:00:10Z","metadata":{"arrival_time":"2026-01-08T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87098,"modality":"semantic_status","timestamp":"2026-01-08T12:00:20Z","metadata":{"arrival_time":"2026-01-08T12:00:31+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-007","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-01-08T12:00:13Z","metadata":{"arrival_time":"2026-01-08T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-08T12:00:10+00:00","obs-2":"2026-01-08T12:00:20+00:00","obs-distractor":"2026-01-08T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-08T12:00:10+00:00","obs-2":"2026-01-08T12:00:31+00:00","obs-distractor":"2026-01-08T12:00:13+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.966,"edge-ai-1":0.597},"confidence":{"obs-1":0.87098,"obs-2":0.87098,"obs-distractor":0.67},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-007-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.700567080723265,"event_time":"2026-01-08T12:00:20+00:00","arrival_time":"2026-01-08T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72147506,"normal":0.27852494000000005},"reference_distribution":{"anomalous":0.299432919276735,"normal":0.700567080723265}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.72147506,"event_time":"2026-01-08T12:00:10+00:00","arrival_time":"2026-01-08T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.72147506,"normal":0.27852494000000005}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-08T12:00:10+00:00","arrival_time":"2026-01-08T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.72147506,"event_time":"2026-01-08T12:00:13+00:00","arrival_time":"2026-01-08T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72147506,"normal":0.27852494000000005},"reference_distribution":{"anomalous":0.72147506,"normal":0.27852494000000005}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-007-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-08T12:00:13+00:00","arrival_time":"2026-01-08T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.700567080723265,"event_time":"2026-01-08T12:00:20+00:00","arrival_time":"2026-01-08T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72147506,"normal":0.27852494000000005},"reference_distribution":{"anomalous":0.299432919276735,"normal":0.700567080723265}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-007-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-08T12:00:20+00:00","arrival_time":"2026-01-08T12:00:31+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":7,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"81fa7ef9c4f625d7946cc7968bcf2fd1ded11fcad4a663f8f868a1121a726623"}}
{"id":"evaluation-v1-source_reliability-20260725-008","name":"Evaluation v1.0 trajectory: source_reliability case 008","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-008","label":"Distractor 008","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87112,"modality":"semantic_status","timestamp":"2026-01-09T12:00:10Z","metadata":{"arrival_time":"2026-01-09T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87112,"modality":"semantic_status","timestamp":"2026-01-09T12:00:20Z","metadata":{"arrival_time":"2026-01-09T12:00:32+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-008","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-01-09T12:00:14Z","metadata":{"arrival_time":"2026-01-09T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-09T12:00:10+00:00","obs-2":"2026-01-09T12:00:20+00:00","obs-distractor":"2026-01-09T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-09T12:00:10+00:00","obs-2":"2026-01-09T12:00:32+00:00","obs-distractor":"2026-01-09T12:00:14+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.974,"edge-ai-1":0.608},"confidence":{"obs-1":0.87112,"obs-2":0.87112,"obs-distractor":0.68},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-008-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7016030129493742,"event_time":"2026-01-09T12:00:20+00:00","arrival_time":"2026-01-09T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72564096,"normal":0.27435904},"reference_distribution":{"anomalous":0.29839698705062573,"normal":0.7016030129493742}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.72564096,"event_time":"2026-01-09T12:00:10+00:00","arrival_time":"2026-01-09T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.72564096,"normal":0.27435904}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-09T12:00:10+00:00","arrival_time":"2026-01-09T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.72564096,"event_time":"2026-01-09T12:00:14+00:00","arrival_time":"2026-01-09T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72564096,"normal":0.27435904},"reference_distribution":{"anomalous":0.72564096,"normal":0.27435904}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-008-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-09T12:00:14+00:00","arrival_time":"2026-01-09T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7016030129493742,"event_time":"2026-01-09T12:00:20+00:00","arrival_time":"2026-01-09T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72564096,"normal":0.27435904},"reference_distribution":{"anomalous":0.29839698705062573,"normal":0.7016030129493742}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-008-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-09T12:00:20+00:00","arrival_time":"2026-01-09T12:00:32+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":8,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"ae0509d60ee0615e8e851cc679f1c8d54c71e63e3c55e26a75df0e85d6650e44"}}
{"id":"evaluation-v1-source_reliability-20260725-009","name":"Evaluation v1.0 trajectory: source_reliability case 009","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-009","label":"Distractor 009","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87126,"modality":"semantic_status","timestamp":"2026-01-10T12:00:10Z","metadata":{"arrival_time":"2026-01-10T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-009","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-01-10T12:00:12Z","metadata":{"arrival_time":"2026-01-10T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87126,"modality":"semantic_status","timestamp":"2026-01-10T12:00:20Z","metadata":{"arrival_time":"2026-01-10T12:00:33+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-10T12:00:10+00:00","obs-distractor":"2026-01-10T12:00:12+00:00","obs-2":"2026-01-10T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-10T12:00:10+00:00","obs-distractor":"2026-01-10T12:00:12+00:00","obs-2":"2026-01-10T12:00:33+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.91,"edge-ai-1":0.619},"confidence":{"obs-1":0.87126,"obs-distractor":0.69,"obs-2":0.87126},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-009-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6567025088687407,"event_time":"2026-01-10T12:00:20+00:00","arrival_time":"2026-01-10T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72980994,"normal":0.27019006},"reference_distribution":{"anomalous":0.3432974911312593,"normal":0.6567025088687407}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.72980994,"event_time":"2026-01-10T12:00:10+00:00","arrival_time":"2026-01-10T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.72980994,"normal":0.27019006}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-10T12:00:10+00:00","arrival_time":"2026-01-10T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.72980994,"event_time":"2026-01-10T12:00:12+00:00","arrival_time":"2026-01-10T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72980994,"normal":0.27019006},"reference_distribution":{"anomalous":0.72980994,"normal":0.27019006}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-009-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-10T12:00:12+00:00","arrival_time":"2026-01-10T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6567025088687407,"event_time":"2026-01-10T12:00:20+00:00","arrival_time":"2026-01-10T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72980994,"normal":0.27019006},"reference_distribution":{"anomalous":0.3432974911312593,"normal":0.6567025088687407}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-009-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-10T12:00:20+00:00","arrival_time":"2026-01-10T12:00:33+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":9,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"38d6c17ea393b7649a0d3e9b71a8ba1169b8292ba238f43e1bf89bde32dde9b6"}}
{"id":"evaluation-v1-source_reliability-20260725-010","name":"Evaluation v1.0 trajectory: source_reliability case 010","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-010","label":"Distractor 010","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8714,"modality":"semantic_status","timestamp":"2026-01-11T12:00:10Z","metadata":{"arrival_time":"2026-01-11T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-010","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.7,"modality":"semantic_status","timestamp":"2026-01-11T12:00:13Z","metadata":{"arrival_time":"2026-01-11T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8714,"modality":"semantic_status","timestamp":"2026-01-11T12:00:20Z","metadata":{"arrival_time":"2026-01-11T12:00:34+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-11T12:00:10+00:00","obs-distractor":"2026-01-11T12:00:13+00:00","obs-2":"2026-01-11T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-11T12:00:10+00:00","obs-distractor":"2026-01-11T12:00:13+00:00","obs-2":"2026-01-11T12:00:34+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.918,"edge-ai-1":0.63},"confidence":{"obs-1":0.8714,"obs-distractor":0.7,"obs-2":0.8714},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-010-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6570909458075089,"event_time":"2026-01-11T12:00:20+00:00","arrival_time":"2026-01-11T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7339819999999999,"normal":0.2660180000000001},"reference_distribution":{"anomalous":0.3429090541924911,"normal":0.6570909458075089}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7339819999999999,"event_time":"2026-01-11T12:00:10+00:00","arrival_time":"2026-01-11T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.7339819999999999,"normal":0.2660180000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-11T12:00:10+00:00","arrival_time":"2026-01-11T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7339819999999999,"event_time":"2026-01-11T12:00:13+00:00","arrival_time":"2026-01-11T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7339819999999999,"normal":0.2660180000000001},"reference_distribution":{"anomalous":0.7339819999999999,"normal":0.2660180000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-010-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-11T12:00:13+00:00","arrival_time":"2026-01-11T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6570909458075089,"event_time":"2026-01-11T12:00:20+00:00","arrival_time":"2026-01-11T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7339819999999999,"normal":0.2660180000000001},"reference_distribution":{"anomalous":0.3429090541924911,"normal":0.6570909458075089}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-010-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-11T12:00:20+00:00","arrival_time":"2026-01-11T12:00:34+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":10,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"376af817c4865ebc113b5c929e76342c6c75817420be1d41456e856bb9fe9ae3"}}
{"id":"evaluation-v1-source_reliability-20260725-011","name":"Evaluation v1.0 trajectory: source_reliability case 011","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-011","label":"Distractor 011","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87154,"modality":"semantic_status","timestamp":"2026-01-12T12:00:10Z","metadata":{"arrival_time":"2026-01-12T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-011","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.71,"modality":"semantic_status","timestamp":"2026-01-12T12:00:14Z","metadata":{"arrival_time":"2026-01-12T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87154,"modality":"semantic_status","timestamp":"2026-01-12T12:00:20Z","metadata":{"arrival_time":"2026-01-12T12:00:35+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-12T12:00:10+00:00","obs-distractor":"2026-01-12T12:00:14+00:00","obs-2":"2026-01-12T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-12T12:00:10+00:00","obs-distractor":"2026-01-12T12:00:14+00:00","obs-2":"2026-01-12T12:00:35+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.926,"edge-ai-1":0.641},"confidence":{"obs-1":0.87154,"obs-distractor":0.71,"obs-2":0.87154},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-011-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6575137198214731,"event_time":"2026-01-12T12:00:20+00:00","arrival_time":"2026-01-12T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.73815714,"normal":0.26184286},"reference_distribution":{"anomalous":0.3424862801785268,"normal":0.6575137198214731}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.73815714,"event_time":"2026-01-12T12:00:10+00:00","arrival_time":"2026-01-12T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.73815714,"normal":0.26184286}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-12T12:00:10+00:00","arrival_time":"2026-01-12T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.73815714,"event_time":"2026-01-12T12:00:14+00:00","arrival_time":"2026-01-12T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.73815714,"normal":0.26184286},"reference_distribution":{"anomalous":0.73815714,"normal":0.26184286}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-011-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-12T12:00:14+00:00","arrival_time":"2026-01-12T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6575137198214731,"event_time":"2026-01-12T12:00:20+00:00","arrival_time":"2026-01-12T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.73815714,"normal":0.26184286},"reference_distribution":{"anomalous":0.3424862801785268,"normal":0.6575137198214731}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-011-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-12T12:00:20+00:00","arrival_time":"2026-01-12T12:00:35+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":11,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"d0c27f6bcfdf6ac27be7ccf660967b24411a76d21412024ed98a84d7417b582d"}}
{"id":"evaluation-v1-source_reliability-20260725-012","name":"Evaluation v1.0 trajectory: source_reliability case 012","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-012","label":"Distractor 012","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87168,"modality":"semantic_status","timestamp":"2026-01-13T12:00:10Z","metadata":{"arrival_time":"2026-01-13T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87168,"modality":"semantic_status","timestamp":"2026-01-13T12:00:20Z","metadata":{"arrival_time":"2026-01-13T12:00:36+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-012","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.72,"modality":"semantic_status","timestamp":"2026-01-13T12:00:12Z","metadata":{"arrival_time":"2026-01-13T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-13T12:00:10+00:00","obs-2":"2026-01-13T12:00:20+00:00","obs-distractor":"2026-01-13T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-13T12:00:10+00:00","obs-2":"2026-01-13T12:00:36+00:00","obs-distractor":"2026-01-13T12:00:12+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.934,"edge-ai-1":0.652},"confidence":{"obs-1":0.87168,"obs-2":0.87168,"obs-distractor":0.72},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-012-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6579724374351026,"event_time":"2026-01-13T12:00:20+00:00","arrival_time":"2026-01-13T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.74233536,"normal":0.25766464},"reference_distribution":{"anomalous":0.34202756256489736,"normal":0.6579724374351026}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.74233536,"event_time":"2026-01-13T12:00:10+00:00","arrival_time":"2026-01-13T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.74233536,"normal":0.25766464}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-13T12:00:10+00:00","arrival_time":"2026-01-13T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.74233536,"event_time":"2026-01-13T12:00:12+00:00","arrival_time":"2026-01-13T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.74233536,"normal":0.25766464},"reference_distribution":{"anomalous":0.74233536,"normal":0.25766464}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-012-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-13T12:00:12+00:00","arrival_time":"2026-01-13T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6579724374351026,"event_time":"2026-01-13T12:00:20+00:00","arrival_time":"2026-01-13T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.74233536,"normal":0.25766464},"reference_distribution":{"anomalous":0.34202756256489736,"normal":0.6579724374351026}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-012-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-13T12:00:20+00:00","arrival_time":"2026-01-13T12:00:36+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":12,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"2d884a8dfcf34710e28fff6a508c6acae85df5e9a6385007776dee19a6fbe831"}}
{"id":"evaluation-v1-source_reliability-20260725-013","name":"Evaluation v1.0 trajectory: source_reliability case 013","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-013","label":"Distractor 013","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87182,"modality":"semantic_status","timestamp":"2026-01-14T12:00:10Z","metadata":{"arrival_time":"2026-01-14T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87182,"modality":"semantic_status","timestamp":"2026-01-14T12:00:20Z","metadata":{"arrival_time":"2026-01-14T12:00:37+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-013","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.73,"modality":"semantic_status","timestamp":"2026-01-14T12:00:13Z","metadata":{"arrival_time":"2026-01-14T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-14T12:00:10+00:00","obs-2":"2026-01-14T12:00:20+00:00","obs-distractor":"2026-01-14T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-14T12:00:10+00:00","obs-2":"2026-01-14T12:00:37+00:00","obs-distractor":"2026-01-14T12:00:13+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.942,"edge-ai-1":0.52},"confidence":{"obs-1":0.87182,"obs-2":0.87182,"obs-distractor":0.73},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-013-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7152024557030581,"event_time":"2026-01-14T12:00:20+00:00","arrival_time":"2026-01-14T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6933464,"normal":0.30665359999999997},"reference_distribution":{"anomalous":0.2847975442969419,"normal":0.7152024557030581}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.6933464,"event_time":"2026-01-14T12:00:10+00:00","arrival_time":"2026-01-14T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.6933464,"normal":0.30665359999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-14T12:00:10+00:00","arrival_time":"2026-01-14T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.6933464,"event_time":"2026-01-14T12:00:13+00:00","arrival_time":"2026-01-14T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6933464,"normal":0.30665359999999997},"reference_distribution":{"anomalous":0.6933464,"normal":0.30665359999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-013-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-14T12:00:13+00:00","arrival_time":"2026-01-14T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7152024557030581,"event_time":"2026-01-14T12:00:20+00:00","arrival_time":"2026-01-14T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6933464,"normal":0.30665359999999997},"reference_distribution":{"anomalous":0.2847975442969419,"normal":0.7152024557030581}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-013-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-14T12:00:20+00:00","arrival_time":"2026-01-14T12:00:37+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":13,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"19d11520989f64de4ad562b62a32e3a75f0ce8ee06a909b859f68fdd3c77deb9"}}
{"id":"evaluation-v1-source_reliability-20260725-014","name":"Evaluation v1.0 trajectory: source_reliability case 014","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-014","label":"Distractor 014","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87196,"modality":"semantic_status","timestamp":"2026-01-15T12:00:10Z","metadata":{"arrival_time":"2026-01-15T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-014","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.74,"modality":"semantic_status","timestamp":"2026-01-15T12:00:14Z","metadata":{"arrival_time":"2026-01-15T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87196,"modality":"semantic_status","timestamp":"2026-01-15T12:00:20Z","metadata":{"arrival_time":"2026-01-15T12:00:38+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-15T12:00:10+00:00","obs-distractor":"2026-01-15T12:00:14+00:00","obs-2":"2026-01-15T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-15T12:00:10+00:00","obs-distractor":"2026-01-15T12:00:14+00:00","obs-2":"2026-01-15T12:00:38+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.95,"edge-ai-1":0.531},"confidence":{"obs-1":0.87196,"obs-distractor":0.74,"obs-2":0.87196},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-014-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7162111690833073,"event_time":"2026-01-15T12:00:20+00:00","arrival_time":"2026-01-15T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.69751076,"normal":0.30248924},"reference_distribution":{"anomalous":0.2837888309166927,"normal":0.7162111690833073}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.69751076,"event_time":"2026-01-15T12:00:10+00:00","arrival_time":"2026-01-15T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.69751076,"normal":0.30248924}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-15T12:00:10+00:00","arrival_time":"2026-01-15T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.69751076,"event_time":"2026-01-15T12:00:14+00:00","arrival_time":"2026-01-15T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.69751076,"normal":0.30248924},"reference_distribution":{"anomalous":0.69751076,"normal":0.30248924}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-014-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-15T12:00:14+00:00","arrival_time":"2026-01-15T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7162111690833073,"event_time":"2026-01-15T12:00:20+00:00","arrival_time":"2026-01-15T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.69751076,"normal":0.30248924},"reference_distribution":{"anomalous":0.2837888309166927,"normal":0.7162111690833073}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-014-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-15T12:00:20+00:00","arrival_time":"2026-01-15T12:00:38+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":14,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"69113f2039276b4f37ec29e744e8daba6fa5010d72c0b3dc00f12caf4702d5b5"}}
{"id":"evaluation-v1-source_reliability-20260725-015","name":"Evaluation v1.0 trajectory: source_reliability case 015","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-015","label":"Distractor 015","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8721,"modality":"semantic_status","timestamp":"2026-01-16T12:00:10Z","metadata":{"arrival_time":"2026-01-16T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-015","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.75,"modality":"semantic_status","timestamp":"2026-01-16T12:00:12Z","metadata":{"arrival_time":"2026-01-16T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8721,"modality":"semantic_status","timestamp":"2026-01-16T12:00:20Z","metadata":{"arrival_time":"2026-01-16T12:00:39+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-16T12:00:10+00:00","obs-distractor":"2026-01-16T12:00:12+00:00","obs-2":"2026-01-16T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-16T12:00:10+00:00","obs-distractor":"2026-01-16T12:00:12+00:00","obs-2":"2026-01-16T12:00:39+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.958,"edge-ai-1":0.542},"confidence":{"obs-1":0.8721,"obs-distractor":0.75,"obs-2":0.8721},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-015-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7172756327869323,"event_time":"2026-01-16T12:00:20+00:00","arrival_time":"2026-01-16T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7016782,"normal":0.29832179999999997},"reference_distribution":{"anomalous":0.2827243672130677,"normal":0.7172756327869323}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7016782,"event_time":"2026-01-16T12:00:10+00:00","arrival_time":"2026-01-16T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.7016782,"normal":0.29832179999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-16T12:00:10+00:00","arrival_time":"2026-01-16T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7016782,"event_time":"2026-01-16T12:00:12+00:00","arrival_time":"2026-01-16T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7016782,"normal":0.29832179999999997},"reference_distribution":{"anomalous":0.7016782,"normal":0.29832179999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-015-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-16T12:00:12+00:00","arrival_time":"2026-01-16T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7172756327869323,"event_time":"2026-01-16T12:00:20+00:00","arrival_time":"2026-01-16T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7016782,"normal":0.29832179999999997},"reference_distribution":{"anomalous":0.2827243672130677,"normal":0.7172756327869323}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-015-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-16T12:00:20+00:00","arrival_time":"2026-01-16T12:00:39+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":15,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"0d237218f9865dd419c6b4e3cfe68e70a52d0c9a421491fc2de6a848f6803fb1"}}
{"id":"evaluation-v1-source_reliability-20260725-016","name":"Evaluation v1.0 trajectory: source_reliability case 016","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-016","label":"Distractor 016","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87224,"modality":"semantic_status","timestamp":"2026-01-17T12:00:10Z","metadata":{"arrival_time":"2026-01-17T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87224,"modality":"semantic_status","timestamp":"2026-01-17T12:00:20Z","metadata":{"arrival_time":"2026-01-17T12:00:40+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-016","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.76,"modality":"semantic_status","timestamp":"2026-01-17T12:00:13Z","metadata":{"arrival_time":"2026-01-17T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-17T12:00:10+00:00","obs-2":"2026-01-17T12:00:20+00:00","obs-distractor":"2026-01-17T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-17T12:00:10+00:00","obs-2":"2026-01-17T12:00:40+00:00","obs-distractor":"2026-01-17T12:00:13+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.966,"edge-ai-1":0.553},"confidence":{"obs-1":0.87224,"obs-2":0.87224,"obs-distractor":0.76},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-016-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7183984106509689,"event_time":"2026-01-17T12:00:20+00:00","arrival_time":"2026-01-17T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70584872,"normal":0.29415128},"reference_distribution":{"anomalous":0.2816015893490312,"normal":0.7183984106509689}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.70584872,"event_time":"2026-01-17T12:00:10+00:00","arrival_time":"2026-01-17T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.70584872,"normal":0.29415128}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-17T12:00:10+00:00","arrival_time":"2026-01-17T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.70584872,"event_time":"2026-01-17T12:00:13+00:00","arrival_time":"2026-01-17T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70584872,"normal":0.29415128},"reference_distribution":{"anomalous":0.70584872,"normal":0.29415128}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-016-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-17T12:00:13+00:00","arrival_time":"2026-01-17T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7183984106509689,"event_time":"2026-01-17T12:00:20+00:00","arrival_time":"2026-01-17T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70584872,"normal":0.29415128},"reference_distribution":{"anomalous":0.2816015893490312,"normal":0.7183984106509689}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-016-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-17T12:00:20+00:00","arrival_time":"2026-01-17T12:00:40+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":16,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"98f48c4a032c0acf6d13dfe091078f10580eb2a12f972a17ac48472e66aaa2fc"}}
{"id":"evaluation-v1-source_reliability-20260725-017","name":"Evaluation v1.0 trajectory: source_reliability case 017","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-017","label":"Distractor 017","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87238,"modality":"semantic_status","timestamp":"2026-01-18T12:00:10Z","metadata":{"arrival_time":"2026-01-18T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-017","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.77,"modality":"semantic_status","timestamp":"2026-01-18T12:00:14Z","metadata":{"arrival_time":"2026-01-18T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87238,"modality":"semantic_status","timestamp":"2026-01-18T12:00:20Z","metadata":{"arrival_time":"2026-01-18T12:00:24+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-18T12:00:10+00:00","obs-distractor":"2026-01-18T12:00:14+00:00","obs-2":"2026-01-18T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-18T12:00:10+00:00","obs-distractor":"2026-01-18T12:00:14+00:00","obs-2":"2026-01-18T12:00:24+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.974,"edge-ai-1":0.564},"confidence":{"obs-1":0.87238,"obs-distractor":0.77,"obs-2":0.87238},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-017-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7195822480190662,"event_time":"2026-01-18T12:00:20+00:00","arrival_time":"2026-01-18T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.71002232,"normal":0.28997768},"reference_distribution":{"anomalous":0.28041775198093377,"normal":0.7195822480190662}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.71002232,"event_time":"2026-01-18T12:00:10+00:00","arrival_time":"2026-01-18T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.71002232,"normal":0.28997768}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-18T12:00:10+00:00","arrival_time":"2026-01-18T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.71002232,"event_time":"2026-01-18T12:00:14+00:00","arrival_time":"2026-01-18T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.71002232,"normal":0.28997768},"reference_distribution":{"anomalous":0.71002232,"normal":0.28997768}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-017-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-18T12:00:14+00:00","arrival_time":"2026-01-18T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7195822480190662,"event_time":"2026-01-18T12:00:20+00:00","arrival_time":"2026-01-18T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.71002232,"normal":0.28997768},"reference_distribution":{"anomalous":0.28041775198093377,"normal":0.7195822480190662}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-017-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-18T12:00:20+00:00","arrival_time":"2026-01-18T12:00:24+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":17,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"1b91e493dcd704bfb901403aff3b4d4f2075586073ef5cd5cf703eb25e6e7003"}}
{"id":"evaluation-v1-source_reliability-20260725-018","name":"Evaluation v1.0 trajectory: source_reliability case 018","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-018","label":"Distractor 018","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87252,"modality":"semantic_status","timestamp":"2026-01-19T12:00:10Z","metadata":{"arrival_time":"2026-01-19T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-018","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.78,"modality":"semantic_status","timestamp":"2026-01-19T12:00:12Z","metadata":{"arrival_time":"2026-01-19T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87252,"modality":"semantic_status","timestamp":"2026-01-19T12:00:20Z","metadata":{"arrival_time":"2026-01-19T12:00:25+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-19T12:00:10+00:00","obs-distractor":"2026-01-19T12:00:12+00:00","obs-2":"2026-01-19T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-19T12:00:10+00:00","obs-distractor":"2026-01-19T12:00:12+00:00","obs-2":"2026-01-19T12:00:25+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.91,"edge-ai-1":0.575},"confidence":{"obs-1":0.87252,"obs-distractor":0.78,"obs-2":0.87252},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-018-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6758774594791749,"event_time":"2026-01-19T12:00:20+00:00","arrival_time":"2026-01-19T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.714199,"normal":0.28580099999999997},"reference_distribution":{"anomalous":0.3241225405208251,"normal":0.6758774594791749}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.714199,"event_time":"2026-01-19T12:00:10+00:00","arrival_time":"2026-01-19T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.714199,"normal":0.28580099999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-19T12:00:10+00:00","arrival_time":"2026-01-19T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.714199,"event_time":"2026-01-19T12:00:12+00:00","arrival_time":"2026-01-19T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.714199,"normal":0.28580099999999997},"reference_distribution":{"anomalous":0.714199,"normal":0.28580099999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-018-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-19T12:00:12+00:00","arrival_time":"2026-01-19T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6758774594791749,"event_time":"2026-01-19T12:00:20+00:00","arrival_time":"2026-01-19T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.714199,"normal":0.28580099999999997},"reference_distribution":{"anomalous":0.3241225405208251,"normal":0.6758774594791749}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-018-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-19T12:00:20+00:00","arrival_time":"2026-01-19T12:00:25+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":18,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"4724e2db196ef9a77f266f133196ec649ce6226af7f340cf98807ff09e040c7d"}}
{"id":"evaluation-v1-source_reliability-20260725-019","name":"Evaluation v1.0 trajectory: source_reliability case 019","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-019","label":"Distractor 019","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87266,"modality":"semantic_status","timestamp":"2026-01-20T12:00:10Z","metadata":{"arrival_time":"2026-01-20T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87266,"modality":"semantic_status","timestamp":"2026-01-20T12:00:20Z","metadata":{"arrival_time":"2026-01-20T12:00:26+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-019","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.79,"modality":"semantic_status","timestamp":"2026-01-20T12:00:13Z","metadata":{"arrival_time":"2026-01-20T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-20T12:00:10+00:00","obs-2":"2026-01-20T12:00:20+00:00","obs-distractor":"2026-01-20T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-20T12:00:10+00:00","obs-2":"2026-01-20T12:00:26+00:00","obs-distractor":"2026-01-20T12:00:13+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.918,"edge-ai-1":0.586},"confidence":{"obs-1":0.87266,"obs-2":0.87266,"obs-distractor":0.79},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-019-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6764526729550709,"event_time":"2026-01-20T12:00:20+00:00","arrival_time":"2026-01-20T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.71837876,"normal":0.28162124},"reference_distribution":{"anomalous":0.323547327044929,"normal":0.6764526729550709}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.71837876,"event_time":"2026-01-20T12:00:10+00:00","arrival_time":"2026-01-20T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.71837876,"normal":0.28162124}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-20T12:00:10+00:00","arrival_time":"2026-01-20T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.71837876,"event_time":"2026-01-20T12:00:13+00:00","arrival_time":"2026-01-20T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.71837876,"normal":0.28162124},"reference_distribution":{"anomalous":0.71837876,"normal":0.28162124}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-019-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-20T12:00:13+00:00","arrival_time":"2026-01-20T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6764526729550709,"event_time":"2026-01-20T12:00:20+00:00","arrival_time":"2026-01-20T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.71837876,"normal":0.28162124},"reference_distribution":{"anomalous":0.323547327044929,"normal":0.6764526729550709}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-019-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-20T12:00:20+00:00","arrival_time":"2026-01-20T12:00:26+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":19,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"ead9e8bb76852d40d636713a239a78543a1463b280b16645a602845c8b93f787"}}
{"id":"evaluation-v1-source_reliability-20260725-020","name":"Evaluation v1.0 trajectory: source_reliability case 020","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-020","label":"Distractor 020","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8728,"modality":"semantic_status","timestamp":"2026-01-21T12:00:10Z","metadata":{"arrival_time":"2026-01-21T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-020","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-01-21T12:00:14Z","metadata":{"arrival_time":"2026-01-21T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8728,"modality":"semantic_status","timestamp":"2026-01-21T12:00:20Z","metadata":{"arrival_time":"2026-01-21T12:00:27+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-21T12:00:10+00:00","obs-distractor":"2026-01-21T12:00:14+00:00","obs-2":"2026-01-21T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-21T12:00:10+00:00","obs-distractor":"2026-01-21T12:00:14+00:00","obs-2":"2026-01-21T12:00:27+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.926,"edge-ai-1":0.597},"confidence":{"obs-1":0.8728,"obs-distractor":0.6,"obs-2":0.8728},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-020-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6770687595815549,"event_time":"2026-01-21T12:00:20+00:00","arrival_time":"2026-01-21T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7225616,"normal":0.2774384},"reference_distribution":{"anomalous":0.3229312404184451,"normal":0.6770687595815549}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7225616,"event_time":"2026-01-21T12:00:10+00:00","arrival_time":"2026-01-21T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.7225616,"normal":0.2774384}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-21T12:00:10+00:00","arrival_time":"2026-01-21T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7225616,"event_time":"2026-01-21T12:00:14+00:00","arrival_time":"2026-01-21T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7225616,"normal":0.2774384},"reference_distribution":{"anomalous":0.7225616,"normal":0.2774384}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-020-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-21T12:00:14+00:00","arrival_time":"2026-01-21T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6770687595815549,"event_time":"2026-01-21T12:00:20+00:00","arrival_time":"2026-01-21T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7225616,"normal":0.2774384},"reference_distribution":{"anomalous":0.3229312404184451,"normal":0.6770687595815549}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-020-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-21T12:00:20+00:00","arrival_time":"2026-01-21T12:00:27+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":20,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"8753a8028eb04b58fe516054db226fcb22d377213ff177c18c9803fe7089c1de"}}
{"id":"evaluation-v1-source_reliability-20260725-021","name":"Evaluation v1.0 trajectory: source_reliability case 021","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-021","label":"Distractor 021","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87294,"modality":"semantic_status","timestamp":"2026-01-22T12:00:10Z","metadata":{"arrival_time":"2026-01-22T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87294,"modality":"semantic_status","timestamp":"2026-01-22T12:00:20Z","metadata":{"arrival_time":"2026-01-22T12:00:28+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-021","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-01-22T12:00:12Z","metadata":{"arrival_time":"2026-01-22T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-22T12:00:10+00:00","obs-2":"2026-01-22T12:00:20+00:00","obs-distractor":"2026-01-22T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-22T12:00:10+00:00","obs-2":"2026-01-22T12:00:28+00:00","obs-distractor":"2026-01-22T12:00:12+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.934,"edge-ai-1":0.608},"confidence":{"obs-1":0.87294,"obs-2":0.87294,"obs-distractor":0.61},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-021-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6777275985952761,"event_time":"2026-01-22T12:00:20+00:00","arrival_time":"2026-01-22T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72674752,"normal":0.27325248},"reference_distribution":{"anomalous":0.32227240140472385,"normal":0.6777275985952761}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.72674752,"event_time":"2026-01-22T12:00:10+00:00","arrival_time":"2026-01-22T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.72674752,"normal":0.27325248}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-22T12:00:10+00:00","arrival_time":"2026-01-22T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.72674752,"event_time":"2026-01-22T12:00:12+00:00","arrival_time":"2026-01-22T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72674752,"normal":0.27325248},"reference_distribution":{"anomalous":0.72674752,"normal":0.27325248}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-021-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-22T12:00:12+00:00","arrival_time":"2026-01-22T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6777275985952761,"event_time":"2026-01-22T12:00:20+00:00","arrival_time":"2026-01-22T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72674752,"normal":0.27325248},"reference_distribution":{"anomalous":0.32227240140472385,"normal":0.6777275985952761}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-021-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-22T12:00:20+00:00","arrival_time":"2026-01-22T12:00:28+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":21,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c4ebcb619d7659537a774b4452be83a21f7d601d56889b0883c30d45c47d489c"}}
{"id":"evaluation-v1-source_reliability-20260725-022","name":"Evaluation v1.0 trajectory: source_reliability case 022","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-022","label":"Distractor 022","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87308,"modality":"semantic_status","timestamp":"2026-01-23T12:00:10Z","metadata":{"arrival_time":"2026-01-23T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-022","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-01-23T12:00:13Z","metadata":{"arrival_time":"2026-01-23T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87308,"modality":"semantic_status","timestamp":"2026-01-23T12:00:20Z","metadata":{"arrival_time":"2026-01-23T12:00:29+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-23T12:00:10+00:00","obs-distractor":"2026-01-23T12:00:13+00:00","obs-2":"2026-01-23T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-23T12:00:10+00:00","obs-distractor":"2026-01-23T12:00:13+00:00","obs-2":"2026-01-23T12:00:29+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.942,"edge-ai-1":0.619},"confidence":{"obs-1":0.87308,"obs-distractor":0.62,"obs-2":0.87308},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-022-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.678431207225197,"event_time":"2026-01-23T12:00:20+00:00","arrival_time":"2026-01-23T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.73093652,"normal":0.26906348},"reference_distribution":{"anomalous":0.32156879277480305,"normal":0.678431207225197}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.73093652,"event_time":"2026-01-23T12:00:10+00:00","arrival_time":"2026-01-23T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.73093652,"normal":0.26906348}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-23T12:00:10+00:00","arrival_time":"2026-01-23T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.73093652,"event_time":"2026-01-23T12:00:13+00:00","arrival_time":"2026-01-23T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.73093652,"normal":0.26906348},"reference_distribution":{"anomalous":0.73093652,"normal":0.26906348}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-022-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-23T12:00:13+00:00","arrival_time":"2026-01-23T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.678431207225197,"event_time":"2026-01-23T12:00:20+00:00","arrival_time":"2026-01-23T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.73093652,"normal":0.26906348},"reference_distribution":{"anomalous":0.32156879277480305,"normal":0.678431207225197}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-022-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-23T12:00:20+00:00","arrival_time":"2026-01-23T12:00:29+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":22,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"b53fbfe10c7084abcfac23ab101d53632b66f3ba2a4e4cb15b81a1dbf2dce92a"}}
{"id":"evaluation-v1-source_reliability-20260725-023","name":"Evaluation v1.0 trajectory: source_reliability case 023","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-023","label":"Distractor 023","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87322,"modality":"semantic_status","timestamp":"2026-01-24T12:00:10Z","metadata":{"arrival_time":"2026-01-24T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-023","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-01-24T12:00:14Z","metadata":{"arrival_time":"2026-01-24T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87322,"modality":"semantic_status","timestamp":"2026-01-24T12:00:20Z","metadata":{"arrival_time":"2026-01-24T12:00:30+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-24T12:00:10+00:00","obs-distractor":"2026-01-24T12:00:14+00:00","obs-2":"2026-01-24T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-24T12:00:10+00:00","obs-distractor":"2026-01-24T12:00:14+00:00","obs-2":"2026-01-24T12:00:30+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.95,"edge-ai-1":0.63},"confidence":{"obs-1":0.87322,"obs-distractor":0.63,"obs-2":0.87322},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-023-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6791817530945758,"event_time":"2026-01-24T12:00:20+00:00","arrival_time":"2026-01-24T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7351286,"normal":0.2648714},"reference_distribution":{"anomalous":0.3208182469054242,"normal":0.6791817530945758}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7351286,"event_time":"2026-01-24T12:00:10+00:00","arrival_time":"2026-01-24T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.7351286,"normal":0.2648714}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-24T12:00:10+00:00","arrival_time":"2026-01-24T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7351286,"event_time":"2026-01-24T12:00:14+00:00","arrival_time":"2026-01-24T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7351286,"normal":0.2648714},"reference_distribution":{"anomalous":0.7351286,"normal":0.2648714}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-023-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-24T12:00:14+00:00","arrival_time":"2026-01-24T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6791817530945758,"event_time":"2026-01-24T12:00:20+00:00","arrival_time":"2026-01-24T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7351286,"normal":0.2648714},"reference_distribution":{"anomalous":0.3208182469054242,"normal":0.6791817530945758}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-023-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-24T12:00:20+00:00","arrival_time":"2026-01-24T12:00:30+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":23,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"077861f748f250d341ef8a882b352f3a8009c297823a4c78b79d0982e2f56f9c"}}
{"id":"evaluation-v1-source_reliability-20260725-024","name":"Evaluation v1.0 trajectory: source_reliability case 024","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-024","label":"Distractor 024","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87336,"modality":"semantic_status","timestamp":"2026-01-25T12:00:10Z","metadata":{"arrival_time":"2026-01-25T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-024","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-01-25T12:00:12Z","metadata":{"arrival_time":"2026-01-25T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87336,"modality":"semantic_status","timestamp":"2026-01-25T12:00:20Z","metadata":{"arrival_time":"2026-01-25T12:00:31+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-25T12:00:10+00:00","obs-distractor":"2026-01-25T12:00:12+00:00","obs-2":"2026-01-25T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-25T12:00:10+00:00","obs-distractor":"2026-01-25T12:00:12+00:00","obs-2":"2026-01-25T12:00:31+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.958,"edge-ai-1":0.641},"confidence":{"obs-1":0.87336,"obs-distractor":0.64,"obs-2":0.87336},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-024-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6799815679970721,"event_time":"2026-01-25T12:00:20+00:00","arrival_time":"2026-01-25T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.73932376,"normal":0.26067624},"reference_distribution":{"anomalous":0.32001843200292784,"normal":0.6799815679970721}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.73932376,"event_time":"2026-01-25T12:00:10+00:00","arrival_time":"2026-01-25T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.73932376,"normal":0.26067624}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-25T12:00:10+00:00","arrival_time":"2026-01-25T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.73932376,"event_time":"2026-01-25T12:00:12+00:00","arrival_time":"2026-01-25T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.73932376,"normal":0.26067624},"reference_distribution":{"anomalous":0.73932376,"normal":0.26067624}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-024-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-25T12:00:12+00:00","arrival_time":"2026-01-25T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6799815679970721,"event_time":"2026-01-25T12:00:20+00:00","arrival_time":"2026-01-25T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.73932376,"normal":0.26067624},"reference_distribution":{"anomalous":0.32001843200292784,"normal":0.6799815679970721}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-024-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-25T12:00:20+00:00","arrival_time":"2026-01-25T12:00:31+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":24,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"470c51768d5243d967816ba8de552752b33d4cefe2eeb9906c7c58d69866a32a"}}
{"id":"evaluation-v1-source_reliability-20260725-025","name":"Evaluation v1.0 trajectory: source_reliability case 025","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-025","label":"Distractor 025","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8735,"modality":"semantic_status","timestamp":"2026-01-26T12:00:10Z","metadata":{"arrival_time":"2026-01-26T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-025","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-01-26T12:00:13Z","metadata":{"arrival_time":"2026-01-26T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8735,"modality":"semantic_status","timestamp":"2026-01-26T12:00:20Z","metadata":{"arrival_time":"2026-01-26T12:00:32+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-26T12:00:10+00:00","obs-distractor":"2026-01-26T12:00:13+00:00","obs-2":"2026-01-26T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-26T12:00:10+00:00","obs-distractor":"2026-01-26T12:00:13+00:00","obs-2":"2026-01-26T12:00:32+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.966,"edge-ai-1":0.652},"confidence":{"obs-1":0.8735,"obs-distractor":0.65,"obs-2":0.8735},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-025-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6808331632275887,"event_time":"2026-01-26T12:00:20+00:00","arrival_time":"2026-01-26T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.743522,"normal":0.256478},"reference_distribution":{"anomalous":0.3191668367724113,"normal":0.6808331632275887}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.743522,"event_time":"2026-01-26T12:00:10+00:00","arrival_time":"2026-01-26T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.743522,"normal":0.256478}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-26T12:00:10+00:00","arrival_time":"2026-01-26T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.743522,"event_time":"2026-01-26T12:00:13+00:00","arrival_time":"2026-01-26T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.743522,"normal":0.256478},"reference_distribution":{"anomalous":0.743522,"normal":0.256478}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-025-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-26T12:00:13+00:00","arrival_time":"2026-01-26T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6808331632275887,"event_time":"2026-01-26T12:00:20+00:00","arrival_time":"2026-01-26T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.743522,"normal":0.256478},"reference_distribution":{"anomalous":0.3191668367724113,"normal":0.6808331632275887}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-025-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-26T12:00:20+00:00","arrival_time":"2026-01-26T12:00:32+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":25,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"f4d9b907b1aff4798b0b4706f3a1966b03e250767a5bfb076850f72555f81309"}}
{"id":"evaluation-v1-source_reliability-20260725-026","name":"Evaluation v1.0 trajectory: source_reliability case 026","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-026","label":"Distractor 026","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87364,"modality":"semantic_status","timestamp":"2026-01-27T12:00:10Z","metadata":{"arrival_time":"2026-01-27T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87364,"modality":"semantic_status","timestamp":"2026-01-27T12:00:20Z","metadata":{"arrival_time":"2026-01-27T12:00:33+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-026","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-01-27T12:00:14Z","metadata":{"arrival_time":"2026-01-27T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-27T12:00:10+00:00","obs-2":"2026-01-27T12:00:20+00:00","obs-distractor":"2026-01-27T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-27T12:00:10+00:00","obs-2":"2026-01-27T12:00:33+00:00","obs-distractor":"2026-01-27T12:00:14+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.974,"edge-ai-1":0.52},"confidence":{"obs-1":0.87364,"obs-2":0.87364,"obs-distractor":0.66},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-026-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7365312353967823,"event_time":"2026-01-27T12:00:20+00:00","arrival_time":"2026-01-27T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6942927999999999,"normal":0.30570720000000007},"reference_distribution":{"anomalous":0.26346876460321755,"normal":0.7365312353967823}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.6942927999999999,"event_time":"2026-01-27T12:00:10+00:00","arrival_time":"2026-01-27T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.6942927999999999,"normal":0.30570720000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-27T12:00:10+00:00","arrival_time":"2026-01-27T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.6942927999999999,"event_time":"2026-01-27T12:00:14+00:00","arrival_time":"2026-01-27T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6942927999999999,"normal":0.30570720000000007},"reference_distribution":{"anomalous":0.6942927999999999,"normal":0.30570720000000007}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-026-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-27T12:00:14+00:00","arrival_time":"2026-01-27T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7365312353967823,"event_time":"2026-01-27T12:00:20+00:00","arrival_time":"2026-01-27T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6942927999999999,"normal":0.30570720000000007},"reference_distribution":{"anomalous":0.26346876460321755,"normal":0.7365312353967823}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-026-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-27T12:00:20+00:00","arrival_time":"2026-01-27T12:00:33+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":26,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"a38ac6e5327d8310bd0ff0d77390f755a18a004e2a8251f0788444b185bee866"}}
{"id":"evaluation-v1-source_reliability-20260725-027","name":"Evaluation v1.0 trajectory: source_reliability case 027","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-027","label":"Distractor 027","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87378,"modality":"semantic_status","timestamp":"2026-01-28T12:00:10Z","metadata":{"arrival_time":"2026-01-28T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87378,"modality":"semantic_status","timestamp":"2026-01-28T12:00:20Z","metadata":{"arrival_time":"2026-01-28T12:00:34+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-027","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-01-28T12:00:12Z","metadata":{"arrival_time":"2026-01-28T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-28T12:00:10+00:00","obs-2":"2026-01-28T12:00:20+00:00","obs-distractor":"2026-01-28T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-01-28T12:00:10+00:00","obs-2":"2026-01-28T12:00:34+00:00","obs-distractor":"2026-01-28T12:00:12+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.91,"edge-ai-1":0.531},"confidence":{"obs-1":0.87378,"obs-2":0.87378,"obs-distractor":0.67},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-027-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6940690050484274,"event_time":"2026-01-28T12:00:20+00:00","arrival_time":"2026-01-28T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.69847718,"normal":0.30152281999999997},"reference_distribution":{"anomalous":0.30593099495157255,"normal":0.6940690050484274}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.69847718,"event_time":"2026-01-28T12:00:10+00:00","arrival_time":"2026-01-28T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.69847718,"normal":0.30152281999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-28T12:00:10+00:00","arrival_time":"2026-01-28T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.69847718,"event_time":"2026-01-28T12:00:12+00:00","arrival_time":"2026-01-28T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.69847718,"normal":0.30152281999999997},"reference_distribution":{"anomalous":0.69847718,"normal":0.30152281999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-027-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-28T12:00:12+00:00","arrival_time":"2026-01-28T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6940690050484274,"event_time":"2026-01-28T12:00:20+00:00","arrival_time":"2026-01-28T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.69847718,"normal":0.30152281999999997},"reference_distribution":{"anomalous":0.30593099495157255,"normal":0.6940690050484274}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-027-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-28T12:00:20+00:00","arrival_time":"2026-01-28T12:00:34+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":27,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c42f3b1cc85301085040dc1469da8baa50b85f1026248179aefb08c3b01dcf6e"}}
{"id":"evaluation-v1-source_reliability-20260725-028","name":"Evaluation v1.0 trajectory: source_reliability case 028","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-028","label":"Distractor 028","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87392,"modality":"semantic_status","timestamp":"2026-01-29T12:00:10Z","metadata":{"arrival_time":"2026-01-29T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87392,"modality":"semantic_status","timestamp":"2026-01-29T12:00:20Z","metadata":{"arrival_time":"2026-01-29T12:00:35+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-028","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-01-29T12:00:13Z","metadata":{"arrival_time":"2026-01-29T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-29T12:00:10+00:00","obs-2":"2026-01-29T12:00:20+00:00","obs-distractor":"2026-01-29T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-01-29T12:00:10+00:00","obs-2":"2026-01-29T12:00:35+00:00","obs-distractor":"2026-01-29T12:00:13+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.918,"edge-ai-1":0.542},"confidence":{"obs-1":0.87392,"obs-2":0.87392,"obs-distractor":0.68},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-028-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6948000518801253,"event_time":"2026-01-29T12:00:20+00:00","arrival_time":"2026-01-29T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7026646400000001,"normal":0.29733535999999994},"reference_distribution":{"anomalous":0.30519994811987466,"normal":0.6948000518801253}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7026646400000001,"event_time":"2026-01-29T12:00:10+00:00","arrival_time":"2026-01-29T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.7026646400000001,"normal":0.29733535999999994}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-29T12:00:10+00:00","arrival_time":"2026-01-29T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7026646400000001,"event_time":"2026-01-29T12:00:13+00:00","arrival_time":"2026-01-29T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7026646400000001,"normal":0.29733535999999994},"reference_distribution":{"anomalous":0.7026646400000001,"normal":0.29733535999999994}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-028-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-29T12:00:13+00:00","arrival_time":"2026-01-29T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6948000518801253,"event_time":"2026-01-29T12:00:20+00:00","arrival_time":"2026-01-29T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7026646400000001,"normal":0.29733535999999994},"reference_distribution":{"anomalous":0.30519994811987466,"normal":0.6948000518801253}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-028-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-29T12:00:20+00:00","arrival_time":"2026-01-29T12:00:35+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":28,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"7e416c2e90883b451c98c167e1408cc7274ddef17f9c4c695a205e35d7a26479"}}
{"id":"evaluation-v1-source_reliability-20260725-029","name":"Evaluation v1.0 trajectory: source_reliability case 029","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-029","label":"Distractor 029","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87406,"modality":"semantic_status","timestamp":"2026-01-30T12:00:10Z","metadata":{"arrival_time":"2026-01-30T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87406,"modality":"semantic_status","timestamp":"2026-01-30T12:00:20Z","metadata":{"arrival_time":"2026-01-30T12:00:36+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-029","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-01-30T12:00:14Z","metadata":{"arrival_time":"2026-01-30T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-01-30T12:00:10+00:00","obs-2":"2026-01-30T12:00:20+00:00","obs-distractor":"2026-01-30T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-01-30T12:00:10+00:00","obs-2":"2026-01-30T12:00:36+00:00","obs-distractor":"2026-01-30T12:00:14+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.926,"edge-ai-1":0.553},"confidence":{"obs-1":0.87406,"obs-2":0.87406,"obs-distractor":0.69},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-029-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6955770925130196,"event_time":"2026-01-30T12:00:20+00:00","arrival_time":"2026-01-30T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70685518,"normal":0.29314482},"reference_distribution":{"anomalous":0.3044229074869804,"normal":0.6955770925130196}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.70685518,"event_time":"2026-01-30T12:00:10+00:00","arrival_time":"2026-01-30T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.70685518,"normal":0.29314482}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-30T12:00:10+00:00","arrival_time":"2026-01-30T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.70685518,"event_time":"2026-01-30T12:00:14+00:00","arrival_time":"2026-01-30T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70685518,"normal":0.29314482},"reference_distribution":{"anomalous":0.70685518,"normal":0.29314482}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-029-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-30T12:00:14+00:00","arrival_time":"2026-01-30T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6955770925130196,"event_time":"2026-01-30T12:00:20+00:00","arrival_time":"2026-01-30T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70685518,"normal":0.29314482},"reference_distribution":{"anomalous":0.3044229074869804,"normal":0.6955770925130196}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-029-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-30T12:00:20+00:00","arrival_time":"2026-01-30T12:00:36+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":29,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"70e83e0419e3f7b3573d07298670f5b78460e65859efc606be30263eb544299f"}}
{"id":"evaluation-v1-source_reliability-20260725-030","name":"Evaluation v1.0 trajectory: source_reliability case 030","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-030","label":"Distractor 030","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8742,"modality":"semantic_status","timestamp":"2026-01-31T12:00:10Z","metadata":{"arrival_time":"2026-01-31T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-030","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.7,"modality":"semantic_status","timestamp":"2026-01-31T12:00:12Z","metadata":{"arrival_time":"2026-01-31T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8742,"modality":"semantic_status","timestamp":"2026-01-31T12:00:20Z","metadata":{"arrival_time":"2026-01-31T12:00:37+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-01-31T12:00:10+00:00","obs-distractor":"2026-01-31T12:00:12+00:00","obs-2":"2026-01-31T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-01-31T12:00:10+00:00","obs-distractor":"2026-01-31T12:00:12+00:00","obs-2":"2026-01-31T12:00:37+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.934,"edge-ai-1":0.564},"confidence":{"obs-1":0.8742,"obs-distractor":0.7,"obs-2":0.8742},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-030-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6964021878375646,"event_time":"2026-01-31T12:00:20+00:00","arrival_time":"2026-01-31T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7110487999999999,"normal":0.2889512000000001},"reference_distribution":{"anomalous":0.3035978121624354,"normal":0.6964021878375646}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7110487999999999,"event_time":"2026-01-31T12:00:10+00:00","arrival_time":"2026-01-31T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.7110487999999999,"normal":0.2889512000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-31T12:00:10+00:00","arrival_time":"2026-01-31T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7110487999999999,"event_time":"2026-01-31T12:00:12+00:00","arrival_time":"2026-01-31T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7110487999999999,"normal":0.2889512000000001},"reference_distribution":{"anomalous":0.7110487999999999,"normal":0.2889512000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-030-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-01-31T12:00:12+00:00","arrival_time":"2026-01-31T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6964021878375646,"event_time":"2026-01-31T12:00:20+00:00","arrival_time":"2026-01-31T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7110487999999999,"normal":0.2889512000000001},"reference_distribution":{"anomalous":0.3035978121624354,"normal":0.6964021878375646}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-030-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-01-31T12:00:20+00:00","arrival_time":"2026-01-31T12:00:37+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":30,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"1098a36b7d730492686b276e2cdf6a20f8a234748dda52558a01a285da436aae"}}
{"id":"evaluation-v1-source_reliability-20260725-031","name":"Evaluation v1.0 trajectory: source_reliability case 031","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-031","label":"Distractor 031","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87434,"modality":"semantic_status","timestamp":"2026-02-01T12:00:10Z","metadata":{"arrival_time":"2026-02-01T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-031","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.71,"modality":"semantic_status","timestamp":"2026-02-01T12:00:13Z","metadata":{"arrival_time":"2026-02-01T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87434,"modality":"semantic_status","timestamp":"2026-02-01T12:00:20Z","metadata":{"arrival_time":"2026-02-01T12:00:38+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-01T12:00:10+00:00","obs-distractor":"2026-02-01T12:00:13+00:00","obs-2":"2026-02-01T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-01T12:00:10+00:00","obs-distractor":"2026-02-01T12:00:13+00:00","obs-2":"2026-02-01T12:00:38+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.942,"edge-ai-1":0.575},"confidence":{"obs-1":0.87434,"obs-distractor":0.71,"obs-2":0.87434},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-031-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6972775450619875,"event_time":"2026-02-01T12:00:20+00:00","arrival_time":"2026-02-01T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7152455,"normal":0.2847545},"reference_distribution":{"anomalous":0.30272245493801253,"normal":0.6972775450619875}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7152455,"event_time":"2026-02-01T12:00:10+00:00","arrival_time":"2026-02-01T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.7152455,"normal":0.2847545}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-01T12:00:10+00:00","arrival_time":"2026-02-01T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7152455,"event_time":"2026-02-01T12:00:13+00:00","arrival_time":"2026-02-01T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7152455,"normal":0.2847545},"reference_distribution":{"anomalous":0.7152455,"normal":0.2847545}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-031-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-01T12:00:13+00:00","arrival_time":"2026-02-01T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6972775450619875,"event_time":"2026-02-01T12:00:20+00:00","arrival_time":"2026-02-01T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7152455,"normal":0.2847545},"reference_distribution":{"anomalous":0.30272245493801253,"normal":0.6972775450619875}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-031-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-01T12:00:20+00:00","arrival_time":"2026-02-01T12:00:38+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":31,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"6676c442518eab220d770ed904e186d45bc2826c8520f1b29bb2d234576e56e7"}}
{"id":"evaluation-v1-source_reliability-20260725-032","name":"Evaluation v1.0 trajectory: source_reliability case 032","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-032","label":"Distractor 032","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87448,"modality":"semantic_status","timestamp":"2026-02-02T12:00:10Z","metadata":{"arrival_time":"2026-02-02T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87448,"modality":"semantic_status","timestamp":"2026-02-02T12:00:20Z","metadata":{"arrival_time":"2026-02-02T12:00:39+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-032","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.72,"modality":"semantic_status","timestamp":"2026-02-02T12:00:14Z","metadata":{"arrival_time":"2026-02-02T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-02T12:00:10+00:00","obs-2":"2026-02-02T12:00:20+00:00","obs-distractor":"2026-02-02T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-02T12:00:10+00:00","obs-2":"2026-02-02T12:00:39+00:00","obs-distractor":"2026-02-02T12:00:14+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.95,"edge-ai-1":0.586},"confidence":{"obs-1":0.87448,"obs-2":0.87448,"obs-distractor":0.72},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-032-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6982055304229073,"event_time":"2026-02-02T12:00:20+00:00","arrival_time":"2026-02-02T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.71944528,"normal":0.28055472000000004},"reference_distribution":{"anomalous":0.30179446957709266,"normal":0.6982055304229073}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.71944528,"event_time":"2026-02-02T12:00:10+00:00","arrival_time":"2026-02-02T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.71944528,"normal":0.28055472000000004}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-02T12:00:10+00:00","arrival_time":"2026-02-02T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.71944528,"event_time":"2026-02-02T12:00:14+00:00","arrival_time":"2026-02-02T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.71944528,"normal":0.28055472000000004},"reference_distribution":{"anomalous":0.71944528,"normal":0.28055472000000004}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-032-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-02T12:00:14+00:00","arrival_time":"2026-02-02T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6982055304229073,"event_time":"2026-02-02T12:00:20+00:00","arrival_time":"2026-02-02T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.71944528,"normal":0.28055472000000004},"reference_distribution":{"anomalous":0.30179446957709266,"normal":0.6982055304229073}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-032-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-02T12:00:20+00:00","arrival_time":"2026-02-02T12:00:39+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":32,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"f600a9a18c100d1afb16399e4552cbf9806c5ea0e771e042771703b13541c091"}}
{"id":"evaluation-v1-source_reliability-20260725-033","name":"Evaluation v1.0 trajectory: source_reliability case 033","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-033","label":"Distractor 033","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87462,"modality":"semantic_status","timestamp":"2026-02-03T12:00:10Z","metadata":{"arrival_time":"2026-02-03T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-033","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.73,"modality":"semantic_status","timestamp":"2026-02-03T12:00:12Z","metadata":{"arrival_time":"2026-02-03T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87462,"modality":"semantic_status","timestamp":"2026-02-03T12:00:20Z","metadata":{"arrival_time":"2026-02-03T12:00:40+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-03T12:00:10+00:00","obs-distractor":"2026-02-03T12:00:12+00:00","obs-2":"2026-02-03T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-03T12:00:10+00:00","obs-distractor":"2026-02-03T12:00:12+00:00","obs-2":"2026-02-03T12:00:40+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.958,"edge-ai-1":0.597},"confidence":{"obs-1":0.87462,"obs-distractor":0.73,"obs-2":0.87462},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-033-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6991886832567875,"event_time":"2026-02-03T12:00:20+00:00","arrival_time":"2026-02-03T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72364814,"normal":0.27635186},"reference_distribution":{"anomalous":0.3008113167432125,"normal":0.6991886832567875}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.72364814,"event_time":"2026-02-03T12:00:10+00:00","arrival_time":"2026-02-03T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.72364814,"normal":0.27635186}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-03T12:00:10+00:00","arrival_time":"2026-02-03T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.72364814,"event_time":"2026-02-03T12:00:12+00:00","arrival_time":"2026-02-03T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72364814,"normal":0.27635186},"reference_distribution":{"anomalous":0.72364814,"normal":0.27635186}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-033-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-03T12:00:12+00:00","arrival_time":"2026-02-03T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6991886832567875,"event_time":"2026-02-03T12:00:20+00:00","arrival_time":"2026-02-03T12:00:40+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72364814,"normal":0.27635186},"reference_distribution":{"anomalous":0.3008113167432125,"normal":0.6991886832567875}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-033-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-03T12:00:20+00:00","arrival_time":"2026-02-03T12:00:40+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":33,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"45cf44ffe5fe7e6ea590b2193b87dd61e5487af9c0d0f4a5e1f4ad0b844990aa"}}
{"id":"evaluation-v1-source_reliability-20260725-034","name":"Evaluation v1.0 trajectory: source_reliability case 034","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-034","label":"Distractor 034","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87476,"modality":"semantic_status","timestamp":"2026-02-04T12:00:10Z","metadata":{"arrival_time":"2026-02-04T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87476,"modality":"semantic_status","timestamp":"2026-02-04T12:00:20Z","metadata":{"arrival_time":"2026-02-04T12:00:24+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-034","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.74,"modality":"semantic_status","timestamp":"2026-02-04T12:00:13Z","metadata":{"arrival_time":"2026-02-04T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-04T12:00:10+00:00","obs-2":"2026-02-04T12:00:20+00:00","obs-distractor":"2026-02-04T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-04T12:00:10+00:00","obs-2":"2026-02-04T12:00:24+00:00","obs-distractor":"2026-02-04T12:00:13+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.966,"edge-ai-1":0.608},"confidence":{"obs-1":0.87476,"obs-2":0.87476,"obs-distractor":0.74},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-034-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.700229731604925,"event_time":"2026-02-04T12:00:20+00:00","arrival_time":"2026-02-04T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72785408,"normal":0.27214592000000004},"reference_distribution":{"anomalous":0.29977026839507503,"normal":0.700229731604925}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.72785408,"event_time":"2026-02-04T12:00:10+00:00","arrival_time":"2026-02-04T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.72785408,"normal":0.27214592000000004}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-04T12:00:10+00:00","arrival_time":"2026-02-04T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.72785408,"event_time":"2026-02-04T12:00:13+00:00","arrival_time":"2026-02-04T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72785408,"normal":0.27214592000000004},"reference_distribution":{"anomalous":0.72785408,"normal":0.27214592000000004}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-034-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-04T12:00:13+00:00","arrival_time":"2026-02-04T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.700229731604925,"event_time":"2026-02-04T12:00:20+00:00","arrival_time":"2026-02-04T12:00:24+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72785408,"normal":0.27214592000000004},"reference_distribution":{"anomalous":0.29977026839507503,"normal":0.700229731604925}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-034-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-04T12:00:20+00:00","arrival_time":"2026-02-04T12:00:24+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":34,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"d4f20e55d750a6703c8c70639a8bb956f7512ac885da6d7b6002d51a212a5e3b"}}
{"id":"evaluation-v1-source_reliability-20260725-035","name":"Evaluation v1.0 trajectory: source_reliability case 035","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-035","label":"Distractor 035","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8749,"modality":"semantic_status","timestamp":"2026-02-05T12:00:10Z","metadata":{"arrival_time":"2026-02-05T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8749,"modality":"semantic_status","timestamp":"2026-02-05T12:00:20Z","metadata":{"arrival_time":"2026-02-05T12:00:25+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-035","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.75,"modality":"semantic_status","timestamp":"2026-02-05T12:00:14Z","metadata":{"arrival_time":"2026-02-05T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-05T12:00:10+00:00","obs-2":"2026-02-05T12:00:20+00:00","obs-distractor":"2026-02-05T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-05T12:00:10+00:00","obs-2":"2026-02-05T12:00:25+00:00","obs-distractor":"2026-02-05T12:00:14+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.974,"edge-ai-1":0.619},"confidence":{"obs-1":0.8749,"obs-2":0.8749,"obs-distractor":0.75},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-035-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7013316095501981,"event_time":"2026-02-05T12:00:20+00:00","arrival_time":"2026-02-05T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7320631,"normal":0.26793690000000003},"reference_distribution":{"anomalous":0.29866839044980187,"normal":0.7013316095501981}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7320631,"event_time":"2026-02-05T12:00:10+00:00","arrival_time":"2026-02-05T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.7320631,"normal":0.26793690000000003}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-05T12:00:10+00:00","arrival_time":"2026-02-05T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7320631,"event_time":"2026-02-05T12:00:14+00:00","arrival_time":"2026-02-05T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7320631,"normal":0.26793690000000003},"reference_distribution":{"anomalous":0.7320631,"normal":0.26793690000000003}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-035-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-05T12:00:14+00:00","arrival_time":"2026-02-05T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7013316095501981,"event_time":"2026-02-05T12:00:20+00:00","arrival_time":"2026-02-05T12:00:25+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7320631,"normal":0.26793690000000003},"reference_distribution":{"anomalous":0.29866839044980187,"normal":0.7013316095501981}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-035-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-05T12:00:20+00:00","arrival_time":"2026-02-05T12:00:25+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":35,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"25b0f7b245a91e645f2d0b42541d4fdd3ef5687b990831783bef76843e93f5f7"}}
{"id":"evaluation-v1-source_reliability-20260725-036","name":"Evaluation v1.0 trajectory: source_reliability case 036","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-036","label":"Distractor 036","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87504,"modality":"semantic_status","timestamp":"2026-02-06T12:00:10Z","metadata":{"arrival_time":"2026-02-06T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87504,"modality":"semantic_status","timestamp":"2026-02-06T12:00:20Z","metadata":{"arrival_time":"2026-02-06T12:00:26+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-036","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.76,"modality":"semantic_status","timestamp":"2026-02-06T12:00:12Z","metadata":{"arrival_time":"2026-02-06T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-06T12:00:10+00:00","obs-2":"2026-02-06T12:00:20+00:00","obs-distractor":"2026-02-06T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-06T12:00:10+00:00","obs-2":"2026-02-06T12:00:26+00:00","obs-distractor":"2026-02-06T12:00:12+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.91,"edge-ai-1":0.63},"confidence":{"obs-1":0.87504,"obs-2":0.87504,"obs-distractor":0.76},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-036-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6550095323628121,"event_time":"2026-02-06T12:00:20+00:00","arrival_time":"2026-02-06T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7362752,"normal":0.2637248},"reference_distribution":{"anomalous":0.34499046763718794,"normal":0.6550095323628121}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7362752,"event_time":"2026-02-06T12:00:10+00:00","arrival_time":"2026-02-06T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.7362752,"normal":0.2637248}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-06T12:00:10+00:00","arrival_time":"2026-02-06T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7362752,"event_time":"2026-02-06T12:00:12+00:00","arrival_time":"2026-02-06T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7362752,"normal":0.2637248},"reference_distribution":{"anomalous":0.7362752,"normal":0.2637248}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-036-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-06T12:00:12+00:00","arrival_time":"2026-02-06T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6550095323628121,"event_time":"2026-02-06T12:00:20+00:00","arrival_time":"2026-02-06T12:00:26+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7362752,"normal":0.2637248},"reference_distribution":{"anomalous":0.34499046763718794,"normal":0.6550095323628121}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-036-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-06T12:00:20+00:00","arrival_time":"2026-02-06T12:00:26+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":36,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"bfcf48b1b89fe4fcf5a8a80b84d30459090791bdd43f692a3e5c84a22082ea8f"}}
{"id":"evaluation-v1-source_reliability-20260725-037","name":"Evaluation v1.0 trajectory: source_reliability case 037","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.641}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-037","label":"Distractor 037","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87518,"modality":"semantic_status","timestamp":"2026-02-07T12:00:10Z","metadata":{"arrival_time":"2026-02-07T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-037","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.77,"modality":"semantic_status","timestamp":"2026-02-07T12:00:13Z","metadata":{"arrival_time":"2026-02-07T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87518,"modality":"semantic_status","timestamp":"2026-02-07T12:00:20Z","metadata":{"arrival_time":"2026-02-07T12:00:27+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-07T12:00:10+00:00","obs-distractor":"2026-02-07T12:00:13+00:00","obs-2":"2026-02-07T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-07T12:00:10+00:00","obs-distractor":"2026-02-07T12:00:13+00:00","obs-2":"2026-02-07T12:00:27+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.918,"edge-ai-1":0.641},"confidence":{"obs-1":0.87518,"obs-distractor":0.77,"obs-2":0.87518},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-037-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.655416581613344,"event_time":"2026-02-07T12:00:20+00:00","arrival_time":"2026-02-07T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.74049038,"normal":0.25950962},"reference_distribution":{"anomalous":0.344583418386656,"normal":0.655416581613344}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.74049038,"event_time":"2026-02-07T12:00:10+00:00","arrival_time":"2026-02-07T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.74049038,"normal":0.25950962}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-07T12:00:10+00:00","arrival_time":"2026-02-07T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.74049038,"event_time":"2026-02-07T12:00:13+00:00","arrival_time":"2026-02-07T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.74049038,"normal":0.25950962},"reference_distribution":{"anomalous":0.74049038,"normal":0.25950962}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-037-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-07T12:00:13+00:00","arrival_time":"2026-02-07T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.655416581613344,"event_time":"2026-02-07T12:00:20+00:00","arrival_time":"2026-02-07T12:00:27+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.74049038,"normal":0.25950962},"reference_distribution":{"anomalous":0.344583418386656,"normal":0.655416581613344}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-037-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-07T12:00:20+00:00","arrival_time":"2026-02-07T12:00:27+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":37,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"6f8f53c2eb57d5e6b8ad8b454d9efe56549b7147b2637b91174bea9d7ffec2fd"}}
{"id":"evaluation-v1-source_reliability-20260725-038","name":"Evaluation v1.0 trajectory: source_reliability case 038","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.652}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-038","label":"Distractor 038","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87532,"modality":"semantic_status","timestamp":"2026-02-08T12:00:10Z","metadata":{"arrival_time":"2026-02-08T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-038","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.78,"modality":"semantic_status","timestamp":"2026-02-08T12:00:14Z","metadata":{"arrival_time":"2026-02-08T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87532,"modality":"semantic_status","timestamp":"2026-02-08T12:00:20Z","metadata":{"arrival_time":"2026-02-08T12:00:28+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-08T12:00:10+00:00","obs-distractor":"2026-02-08T12:00:14+00:00","obs-2":"2026-02-08T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-08T12:00:10+00:00","obs-distractor":"2026-02-08T12:00:14+00:00","obs-2":"2026-02-08T12:00:28+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.926,"edge-ai-1":0.652},"confidence":{"obs-1":0.87532,"obs-distractor":0.78,"obs-2":0.87532},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-038-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6558596178124004,"event_time":"2026-02-08T12:00:20+00:00","arrival_time":"2026-02-08T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.74470864,"normal":0.25529135999999997},"reference_distribution":{"anomalous":0.34414038218759957,"normal":0.6558596178124004}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.74470864,"event_time":"2026-02-08T12:00:10+00:00","arrival_time":"2026-02-08T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.74470864,"normal":0.25529135999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-08T12:00:10+00:00","arrival_time":"2026-02-08T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.74470864,"event_time":"2026-02-08T12:00:14+00:00","arrival_time":"2026-02-08T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.74470864,"normal":0.25529135999999997},"reference_distribution":{"anomalous":0.74470864,"normal":0.25529135999999997}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-038-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-08T12:00:14+00:00","arrival_time":"2026-02-08T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6558596178124004,"event_time":"2026-02-08T12:00:20+00:00","arrival_time":"2026-02-08T12:00:28+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.74470864,"normal":0.25529135999999997},"reference_distribution":{"anomalous":0.34414038218759957,"normal":0.6558596178124004}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-038-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-08T12:00:20+00:00","arrival_time":"2026-02-08T12:00:28+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":38,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"a21d4564a9da0102497f47871d945a9a30d5e8130805e0ad223d1e8eda600ed3"}}
{"id":"evaluation-v1-source_reliability-20260725-039","name":"Evaluation v1.0 trajectory: source_reliability case 039","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.834}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.52}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-039","label":"Distractor 039","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87546,"modality":"semantic_status","timestamp":"2026-02-09T12:00:10Z","metadata":{"arrival_time":"2026-02-09T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-039","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.79,"modality":"semantic_status","timestamp":"2026-02-09T12:00:12Z","metadata":{"arrival_time":"2026-02-09T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87546,"modality":"semantic_status","timestamp":"2026-02-09T12:00:20Z","metadata":{"arrival_time":"2026-02-09T12:00:29+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-09T12:00:10+00:00","obs-distractor":"2026-02-09T12:00:12+00:00","obs-2":"2026-02-09T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-09T12:00:10+00:00","obs-distractor":"2026-02-09T12:00:12+00:00","obs-2":"2026-02-09T12:00:29+00:00"},"source_reliability":{"robot-1":0.834,"iot-sensor-1":0.934,"edge-ai-1":0.52},"confidence":{"obs-1":0.87546,"obs-distractor":0.79,"obs-2":0.87546},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-039-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7140656751585847,"event_time":"2026-02-09T12:00:20+00:00","arrival_time":"2026-02-09T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6952392000000001,"normal":0.30476079999999994},"reference_distribution":{"anomalous":0.2859343248414154,"normal":0.7140656751585847}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.6952392000000001,"event_time":"2026-02-09T12:00:10+00:00","arrival_time":"2026-02-09T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.6952392000000001,"normal":0.30476079999999994}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-09T12:00:10+00:00","arrival_time":"2026-02-09T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.6952392000000001,"event_time":"2026-02-09T12:00:12+00:00","arrival_time":"2026-02-09T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6952392000000001,"normal":0.30476079999999994},"reference_distribution":{"anomalous":0.6952392000000001,"normal":0.30476079999999994}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-039-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-09T12:00:12+00:00","arrival_time":"2026-02-09T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7140656751585847,"event_time":"2026-02-09T12:00:20+00:00","arrival_time":"2026-02-09T12:00:29+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6952392000000001,"normal":0.30476079999999994},"reference_distribution":{"anomalous":0.2859343248414154,"normal":0.7140656751585847}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-039-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-09T12:00:20+00:00","arrival_time":"2026-02-09T12:00:29+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":39,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"f0d2bb9a9ecbdef1549aece2be761a14705869a80e0e9056a6c95f55ecb3d144"}}
{"id":"evaluation-v1-source_reliability-20260725-040","name":"Evaluation v1.0 trajectory: source_reliability case 040","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.843}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.531}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-040","label":"Distractor 040","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8756,"modality":"semantic_status","timestamp":"2026-02-10T12:00:10Z","metadata":{"arrival_time":"2026-02-10T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8756,"modality":"semantic_status","timestamp":"2026-02-10T12:00:20Z","metadata":{"arrival_time":"2026-02-10T12:00:30+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-040","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.6,"modality":"semantic_status","timestamp":"2026-02-10T12:00:13Z","metadata":{"arrival_time":"2026-02-10T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-10T12:00:10+00:00","obs-2":"2026-02-10T12:00:20+00:00","obs-distractor":"2026-02-10T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-10T12:00:10+00:00","obs-2":"2026-02-10T12:00:30+00:00","obs-distractor":"2026-02-10T12:00:13+00:00"},"source_reliability":{"robot-1":0.843,"iot-sensor-1":0.942,"edge-ai-1":0.531},"confidence":{"obs-1":0.8756,"obs-2":0.8756,"obs-distractor":0.6},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-040-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7150815236651507,"event_time":"2026-02-10T12:00:20+00:00","arrival_time":"2026-02-10T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6994436,"normal":0.30055639999999995},"reference_distribution":{"anomalous":0.2849184763348494,"normal":0.7150815236651507}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.6994436,"event_time":"2026-02-10T12:00:10+00:00","arrival_time":"2026-02-10T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.6994436,"normal":0.30055639999999995}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-10T12:00:10+00:00","arrival_time":"2026-02-10T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.6994436,"event_time":"2026-02-10T12:00:13+00:00","arrival_time":"2026-02-10T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6994436,"normal":0.30055639999999995},"reference_distribution":{"anomalous":0.6994436,"normal":0.30055639999999995}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-040-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-10T12:00:13+00:00","arrival_time":"2026-02-10T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7150815236651507,"event_time":"2026-02-10T12:00:20+00:00","arrival_time":"2026-02-10T12:00:30+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.6994436,"normal":0.30055639999999995},"reference_distribution":{"anomalous":0.2849184763348494,"normal":0.7150815236651507}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-040-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-10T12:00:20+00:00","arrival_time":"2026-02-10T12:00:30+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":40,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"1d25a0bb7699662b9a99d1eaac74f36bef17f765078ab4ac18fb4e9e7c46fd93"}}
{"id":"evaluation-v1-source_reliability-20260725-041","name":"Evaluation v1.0 trajectory: source_reliability case 041","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.852}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.95}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.542}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-041","label":"Distractor 041","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87574,"modality":"semantic_status","timestamp":"2026-02-11T12:00:10Z","metadata":{"arrival_time":"2026-02-11T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-041","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.61,"modality":"semantic_status","timestamp":"2026-02-11T12:00:14Z","metadata":{"arrival_time":"2026-02-11T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87574,"modality":"semantic_status","timestamp":"2026-02-11T12:00:20Z","metadata":{"arrival_time":"2026-02-11T12:00:31+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.81,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-11T12:00:10+00:00","obs-distractor":"2026-02-11T12:00:14+00:00","obs-2":"2026-02-11T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-11T12:00:10+00:00","obs-distractor":"2026-02-11T12:00:14+00:00","obs-2":"2026-02-11T12:00:31+00:00"},"source_reliability":{"robot-1":0.852,"iot-sensor-1":0.95,"edge-ai-1":0.542},"confidence":{"obs-1":0.87574,"obs-distractor":0.61,"obs-2":0.87574},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-041-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7161542790103415,"event_time":"2026-02-11T12:00:20+00:00","arrival_time":"2026-02-11T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70365108,"normal":0.29634892},"reference_distribution":{"anomalous":0.28384572098965855,"normal":0.7161542790103415}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.70365108,"event_time":"2026-02-11T12:00:10+00:00","arrival_time":"2026-02-11T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.70365108,"normal":0.29634892}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-11T12:00:10+00:00","arrival_time":"2026-02-11T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.70365108,"event_time":"2026-02-11T12:00:14+00:00","arrival_time":"2026-02-11T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70365108,"normal":0.29634892},"reference_distribution":{"anomalous":0.70365108,"normal":0.29634892}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-041-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-11T12:00:14+00:00","arrival_time":"2026-02-11T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7161542790103415,"event_time":"2026-02-11T12:00:20+00:00","arrival_time":"2026-02-11T12:00:31+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70365108,"normal":0.29634892},"reference_distribution":{"anomalous":0.28384572098965855,"normal":0.7161542790103415}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-041-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-11T12:00:20+00:00","arrival_time":"2026-02-11T12:00:31+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":41,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c15fc1e29ef9654d17b16084885fe8c8ae64e3352d15e5138b8013536a3b5785"}}
{"id":"evaluation-v1-source_reliability-20260725-042","name":"Evaluation v1.0 trajectory: source_reliability case 042","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.861}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.958}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.553}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-042","label":"Distractor 042","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87588,"modality":"semantic_status","timestamp":"2026-02-12T12:00:10Z","metadata":{"arrival_time":"2026-02-12T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87588,"modality":"semantic_status","timestamp":"2026-02-12T12:00:20Z","metadata":{"arrival_time":"2026-02-12T12:00:32+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-042","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.62,"modality":"semantic_status","timestamp":"2026-02-12T12:00:12Z","metadata":{"arrival_time":"2026-02-12T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8200000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-12T12:00:10+00:00","obs-2":"2026-02-12T12:00:20+00:00","obs-distractor":"2026-02-12T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-12T12:00:10+00:00","obs-2":"2026-02-12T12:00:32+00:00","obs-distractor":"2026-02-12T12:00:12+00:00"},"source_reliability":{"robot-1":0.861,"iot-sensor-1":0.958,"edge-ai-1":0.553},"confidence":{"obs-1":0.87588,"obs-2":0.87588,"obs-distractor":0.62},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-042-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7172865991552978,"event_time":"2026-02-12T12:00:20+00:00","arrival_time":"2026-02-12T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70786164,"normal":0.29213836000000004},"reference_distribution":{"anomalous":0.28271340084470215,"normal":0.7172865991552978}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.70786164,"event_time":"2026-02-12T12:00:10+00:00","arrival_time":"2026-02-12T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.70786164,"normal":0.29213836000000004}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-12T12:00:10+00:00","arrival_time":"2026-02-12T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.70786164,"event_time":"2026-02-12T12:00:12+00:00","arrival_time":"2026-02-12T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70786164,"normal":0.29213836000000004},"reference_distribution":{"anomalous":0.70786164,"normal":0.29213836000000004}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-042-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-12T12:00:12+00:00","arrival_time":"2026-02-12T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7172865991552978,"event_time":"2026-02-12T12:00:20+00:00","arrival_time":"2026-02-12T12:00:32+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.70786164,"normal":0.29213836000000004},"reference_distribution":{"anomalous":0.28271340084470215,"normal":0.7172865991552978}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-042-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-12T12:00:20+00:00","arrival_time":"2026-02-12T12:00:32+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":42,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"39edd3fb0a8ffcdee160383b20ca86dc3bdc7cb5595289a53f0ee3e8c117cd04"}}
{"id":"evaluation-v1-source_reliability-20260725-043","name":"Evaluation v1.0 trajectory: source_reliability case 043","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.87}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.966}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.564}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-043","label":"Distractor 043","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87602,"modality":"semantic_status","timestamp":"2026-02-13T12:00:10Z","metadata":{"arrival_time":"2026-02-13T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-043","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.63,"modality":"semantic_status","timestamp":"2026-02-13T12:00:13Z","metadata":{"arrival_time":"2026-02-13T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87602,"modality":"semantic_status","timestamp":"2026-02-13T12:00:20Z","metadata":{"arrival_time":"2026-02-13T12:00:33+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8300000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-13T12:00:10+00:00","obs-distractor":"2026-02-13T12:00:13+00:00","obs-2":"2026-02-13T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-13T12:00:10+00:00","obs-distractor":"2026-02-13T12:00:13+00:00","obs-2":"2026-02-13T12:00:33+00:00"},"source_reliability":{"robot-1":0.87,"iot-sensor-1":0.966,"edge-ai-1":0.564},"confidence":{"obs-1":0.87602,"obs-distractor":0.63,"obs-2":0.87602},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-043-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7184813330302834,"event_time":"2026-02-13T12:00:20+00:00","arrival_time":"2026-02-13T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.71207528,"normal":0.28792472},"reference_distribution":{"anomalous":0.2815186669697167,"normal":0.7184813330302834}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.71207528,"event_time":"2026-02-13T12:00:10+00:00","arrival_time":"2026-02-13T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.71207528,"normal":0.28792472}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-13T12:00:10+00:00","arrival_time":"2026-02-13T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.71207528,"event_time":"2026-02-13T12:00:13+00:00","arrival_time":"2026-02-13T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.71207528,"normal":0.28792472},"reference_distribution":{"anomalous":0.71207528,"normal":0.28792472}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-043-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-13T12:00:13+00:00","arrival_time":"2026-02-13T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7184813330302834,"event_time":"2026-02-13T12:00:20+00:00","arrival_time":"2026-02-13T12:00:33+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.71207528,"normal":0.28792472},"reference_distribution":{"anomalous":0.2815186669697167,"normal":0.7184813330302834}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-043-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-13T12:00:20+00:00","arrival_time":"2026-02-13T12:00:33+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":43,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"7812f38488fa3efc76baf09210fd5cc4fe7dfd74b8c5badd18268294e272907f"}}
{"id":"evaluation-v1-source_reliability-20260725-044","name":"Evaluation v1.0 trajectory: source_reliability case 044","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.78}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.974}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.575}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-044","label":"Distractor 044","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87616,"modality":"semantic_status","timestamp":"2026-02-14T12:00:10Z","metadata":{"arrival_time":"2026-02-14T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-044","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.64,"modality":"semantic_status","timestamp":"2026-02-14T12:00:14Z","metadata":{"arrival_time":"2026-02-14T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87616,"modality":"semantic_status","timestamp":"2026-02-14T12:00:20Z","metadata":{"arrival_time":"2026-02-14T12:00:34+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8400000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-14T12:00:10+00:00","obs-distractor":"2026-02-14T12:00:14+00:00","obs-2":"2026-02-14T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-14T12:00:10+00:00","obs-distractor":"2026-02-14T12:00:14+00:00","obs-2":"2026-02-14T12:00:34+00:00"},"source_reliability":{"robot-1":0.78,"iot-sensor-1":0.974,"edge-ai-1":0.575},"confidence":{"obs-1":0.87616,"obs-distractor":0.64,"obs-2":0.87616},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-044-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7197415374682635,"event_time":"2026-02-14T12:00:20+00:00","arrival_time":"2026-02-14T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.716292,"normal":0.28370799999999996},"reference_distribution":{"anomalous":0.2802584625317365,"normal":0.7197415374682635}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.716292,"event_time":"2026-02-14T12:00:10+00:00","arrival_time":"2026-02-14T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.716292,"normal":0.28370799999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-14T12:00:10+00:00","arrival_time":"2026-02-14T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.716292,"event_time":"2026-02-14T12:00:14+00:00","arrival_time":"2026-02-14T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.716292,"normal":0.28370799999999996},"reference_distribution":{"anomalous":0.716292,"normal":0.28370799999999996}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-044-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-14T12:00:14+00:00","arrival_time":"2026-02-14T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.7197415374682635,"event_time":"2026-02-14T12:00:20+00:00","arrival_time":"2026-02-14T12:00:34+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.716292,"normal":0.28370799999999996},"reference_distribution":{"anomalous":0.2802584625317365,"normal":0.7197415374682635}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-044-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-14T12:00:20+00:00","arrival_time":"2026-02-14T12:00:34+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":44,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"2c1520ef568a09c7aac9eeb028e35334202f1ad5d560a601e66dc5dd805f2c34"}}
{"id":"evaluation-v1-source_reliability-20260725-045","name":"Evaluation v1.0 trajectory: source_reliability case 045","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.789}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.91}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.586}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-0"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-1"}},{"id":"distractor-045","label":"Distractor 045","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.8763,"modality":"semantic_status","timestamp":"2026-02-15T12:00:10Z","metadata":{"arrival_time":"2026-02-15T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.8763,"modality":"semantic_status","timestamp":"2026-02-15T12:00:20Z","metadata":{"arrival_time":"2026-02-15T12:00:35+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-045","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.65,"modality":"semantic_status","timestamp":"2026-02-15T12:00:12Z","metadata":{"arrival_time":"2026-02-15T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8500000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-15T12:00:10+00:00","obs-2":"2026-02-15T12:00:20+00:00","obs-distractor":"2026-02-15T12:00:12+00:00"},"arrival_times":{"obs-1":"2026-02-15T12:00:10+00:00","obs-2":"2026-02-15T12:00:35+00:00","obs-distractor":"2026-02-15T12:00:12+00:00"},"source_reliability":{"robot-1":0.789,"iot-sensor-1":0.91,"edge-ai-1":0.586},"confidence":{"obs-1":0.8763,"obs-2":0.8763,"obs-distractor":0.65},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-045-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6746827345266337,"event_time":"2026-02-15T12:00:20+00:00","arrival_time":"2026-02-15T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7205117999999999,"normal":0.2794882000000001},"reference_distribution":{"anomalous":0.32531726547336626,"normal":0.6746827345266337}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7205117999999999,"event_time":"2026-02-15T12:00:10+00:00","arrival_time":"2026-02-15T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.7205117999999999,"normal":0.2794882000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-15T12:00:10+00:00","arrival_time":"2026-02-15T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7205117999999999,"event_time":"2026-02-15T12:00:12+00:00","arrival_time":"2026-02-15T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7205117999999999,"normal":0.2794882000000001},"reference_distribution":{"anomalous":0.7205117999999999,"normal":0.2794882000000001}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-045-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-15T12:00:12+00:00","arrival_time":"2026-02-15T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6746827345266337,"event_time":"2026-02-15T12:00:20+00:00","arrival_time":"2026-02-15T12:00:35+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7205117999999999,"normal":0.2794882000000001},"reference_distribution":{"anomalous":0.32531726547336626,"normal":0.6746827345266337}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-045-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-15T12:00:20+00:00","arrival_time":"2026-02-15T12:00:35+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":45,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"c1629b3ddc6e1a40dc7559217e5f0e3015c0bd761ee54d8d7c8044db38192c92"}}
{"id":"evaluation-v1-source_reliability-20260725-046","name":"Evaluation v1.0 trajectory: source_reliability case 046","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.798}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.918}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.597}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-1"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-2"}},{"id":"distractor-046","label":"Distractor 046","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87644,"modality":"semantic_status","timestamp":"2026-02-16T12:00:10Z","metadata":{"arrival_time":"2026-02-16T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87644,"modality":"semantic_status","timestamp":"2026-02-16T12:00:20Z","metadata":{"arrival_time":"2026-02-16T12:00:36+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-046","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.66,"modality":"semantic_status","timestamp":"2026-02-16T12:00:13Z","metadata":{"arrival_time":"2026-02-16T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8600000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-16T12:00:10+00:00","obs-2":"2026-02-16T12:00:20+00:00","obs-distractor":"2026-02-16T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-16T12:00:10+00:00","obs-2":"2026-02-16T12:00:36+00:00","obs-distractor":"2026-02-16T12:00:13+00:00"},"source_reliability":{"robot-1":0.798,"iot-sensor-1":0.918,"edge-ai-1":0.597},"confidence":{"obs-1":0.87644,"obs-2":0.87644,"obs-distractor":0.66},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-046-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6752910507182743,"event_time":"2026-02-16T12:00:20+00:00","arrival_time":"2026-02-16T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72473468,"normal":0.27526532000000004},"reference_distribution":{"anomalous":0.32470894928172567,"normal":0.6752910507182743}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.72473468,"event_time":"2026-02-16T12:00:10+00:00","arrival_time":"2026-02-16T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.72473468,"normal":0.27526532000000004}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-16T12:00:10+00:00","arrival_time":"2026-02-16T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.72473468,"event_time":"2026-02-16T12:00:13+00:00","arrival_time":"2026-02-16T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72473468,"normal":0.27526532000000004},"reference_distribution":{"anomalous":0.72473468,"normal":0.27526532000000004}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-046-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-16T12:00:13+00:00","arrival_time":"2026-02-16T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6752910507182743,"event_time":"2026-02-16T12:00:20+00:00","arrival_time":"2026-02-16T12:00:36+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72473468,"normal":0.27526532000000004},"reference_distribution":{"anomalous":0.32470894928172567,"normal":0.6752910507182743}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-046-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-16T12:00:20+00:00","arrival_time":"2026-02-16T12:00:36+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":46,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"8f1b276bc9e9ea1779776e695e2fb4891a6b5b757fb8c889c2a5d09ba13db2e9"}}
{"id":"evaluation-v1-source_reliability-20260725-047","name":"Evaluation v1.0 trajectory: source_reliability case 047","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.807}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.926}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.608}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-2"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-3"}},{"id":"distractor-047","label":"Distractor 047","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87658,"modality":"semantic_status","timestamp":"2026-02-17T12:00:10Z","metadata":{"arrival_time":"2026-02-17T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87658,"modality":"semantic_status","timestamp":"2026-02-17T12:00:20Z","metadata":{"arrival_time":"2026-02-17T12:00:37+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-047","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.67,"modality":"semantic_status","timestamp":"2026-02-17T12:00:14Z","metadata":{"arrival_time":"2026-02-17T12:00:14+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.8700000000000001,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-17T12:00:10+00:00","obs-2":"2026-02-17T12:00:20+00:00","obs-distractor":"2026-02-17T12:00:14+00:00"},"arrival_times":{"obs-1":"2026-02-17T12:00:10+00:00","obs-2":"2026-02-17T12:00:37+00:00","obs-distractor":"2026-02-17T12:00:14+00:00"},"source_reliability":{"robot-1":0.807,"iot-sensor-1":0.926,"edge-ai-1":0.608},"confidence":{"obs-1":0.87658,"obs-2":0.87658,"obs-distractor":0.67},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-047-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6759425612664601,"event_time":"2026-02-17T12:00:20+00:00","arrival_time":"2026-02-17T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72896064,"normal":0.27103935999999995},"reference_distribution":{"anomalous":0.32405743873353987,"normal":0.6759425612664601}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.72896064,"event_time":"2026-02-17T12:00:10+00:00","arrival_time":"2026-02-17T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.72896064,"normal":0.27103935999999995}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-17T12:00:10+00:00","arrival_time":"2026-02-17T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.72896064,"event_time":"2026-02-17T12:00:14+00:00","arrival_time":"2026-02-17T12:00:14+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72896064,"normal":0.27103935999999995},"reference_distribution":{"anomalous":0.72896064,"normal":0.27103935999999995}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-047-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-17T12:00:14+00:00","arrival_time":"2026-02-17T12:00:14+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6759425612664601,"event_time":"2026-02-17T12:00:20+00:00","arrival_time":"2026-02-17T12:00:37+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.72896064,"normal":0.27103935999999995},"reference_distribution":{"anomalous":0.32405743873353987,"normal":0.6759425612664601}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-047-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-17T12:00:20+00:00","arrival_time":"2026-02-17T12:00:37+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":47,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"aef8ebc9c52346c719788a821416473dc8c15897f2e35373cd84305f2ae7e44c"}}
{"id":"evaluation-v1-source_reliability-20260725-048","name":"Evaluation v1.0 trajectory: source_reliability case 048","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.816}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.934}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.619}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-3"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-4"}},{"id":"distractor-048","label":"Distractor 048","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87672,"modality":"semantic_status","timestamp":"2026-02-18T12:00:10Z","metadata":{"arrival_time":"2026-02-18T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-048","predicate":"indicator","object_id":null,"value":"nominal","confidence":0.68,"modality":"semantic_status","timestamp":"2026-02-18T12:00:12Z","metadata":{"arrival_time":"2026-02-18T12:00:12+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87672,"modality":"semantic_status","timestamp":"2026-02-18T12:00:20Z","metadata":{"arrival_time":"2026-02-18T12:00:38+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.88,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-distractor":"edge-ai-1","obs-2":"iot-sensor-1"},"event_times":{"obs-1":"2026-02-18T12:00:10+00:00","obs-distractor":"2026-02-18T12:00:12+00:00","obs-2":"2026-02-18T12:00:20+00:00"},"arrival_times":{"obs-1":"2026-02-18T12:00:10+00:00","obs-distractor":"2026-02-18T12:00:12+00:00","obs-2":"2026-02-18T12:00:38+00:00"},"source_reliability":{"robot-1":0.816,"iot-sensor-1":0.934,"edge-ai-1":0.619},"confidence":{"obs-1":0.87672,"obs-distractor":0.68,"obs-2":0.87672},"state_epochs":{"obs-1":1,"obs-distractor":1,"obs-2":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-048-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6766393352094373,"event_time":"2026-02-18T12:00:20+00:00","arrival_time":"2026-02-18T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7331896800000001,"normal":0.26681031999999993},"reference_distribution":{"anomalous":0.32336066479056264,"normal":0.6766393352094373}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7331896800000001,"event_time":"2026-02-18T12:00:10+00:00","arrival_time":"2026-02-18T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.7331896800000001,"normal":0.26681031999999993}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-18T12:00:10+00:00","arrival_time":"2026-02-18T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7331896800000001,"event_time":"2026-02-18T12:00:12+00:00","arrival_time":"2026-02-18T12:00:12+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7331896800000001,"normal":0.26681031999999993},"reference_distribution":{"anomalous":0.7331896800000001,"normal":0.26681031999999993}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-048-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-18T12:00:12+00:00","arrival_time":"2026-02-18T12:00:12+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6766393352094373,"event_time":"2026-02-18T12:00:20+00:00","arrival_time":"2026-02-18T12:00:38+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7331896800000001,"normal":0.26681031999999993},"reference_distribution":{"anomalous":0.32336066479056264,"normal":0.6766393352094373}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-048-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-18T12:00:20+00:00","arrival_time":"2026-02-18T12:00:38+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":48,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"9666c207d2ea5720ce01b7f6baa2e992a5ca20e3f0a6efef85c5cda5e9763a59"}}
{"id":"evaluation-v1-source_reliability-20260725-049","name":"Evaluation v1.0 trajectory: source_reliability case 049","agents":[{"id":"robot-1","name":"Robot 1","kind":"robot","capabilities":["status_observation"],"metadata":{"reliability":0.825}},{"id":"iot-sensor-1","name":"Iot Sensor 1","kind":"iot_sensor","capabilities":["status_observation"],"metadata":{"reliability":0.942}},{"id":"edge-ai-1","name":"Edge Ai 1","kind":"edge_ai","capabilities":["status_observation"],"metadata":{"reliability":0.63}}],"objects":[{"id":"gauge-1","label":"Pressure Gauge 1","category":"gauge","attributes":{}},{"id":"gauge-2","label":"Pressure Gauge 2","category":"gauge","attributes":{}},{"id":"sensor-a","label":"Remote Sensor A","category":"sensor","attributes":{"station":"station-4"}},{"id":"sensor-b","label":"Remote Sensor B","category":"sensor","attributes":{"station":"station-0"}},{"id":"distractor-049","label":"Distractor 049","category":"panel","attributes":{}}],"observations":[{"id":"obs-1","agent_id":"edge-ai-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"anomalous","confidence":0.87686,"modality":"semantic_status","timestamp":"2026-02-19T12:00:10Z","metadata":{"arrival_time":"2026-02-19T12:00:10+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-2","agent_id":"iot-sensor-1","subject_id":"gauge-1","predicate":"condition","object_id":null,"value":"normal","confidence":0.87686,"modality":"semantic_status","timestamp":"2026-02-19T12:00:20Z","metadata":{"arrival_time":"2026-02-19T12:00:39+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}},{"id":"obs-distractor","agent_id":"edge-ai-1","subject_id":"distractor-049","predicate":"indicator","object_id":null,"value":"unknown","confidence":0.69,"modality":"semantic_status","timestamp":"2026-02-19T12:00:13Z","metadata":{"arrival_time":"2026-02-19T12:00:13+00:00","state_epoch":1,"supersedes_evidence_ids":[],"benchmark_role":"evaluation_v1_controlled_trajectory"}}],"relations":[{"source_id":"gauge-1","target_id":"gauge-2","predicate":"adjacent_to","confidence":0.89,"evidence_ids":[]}],"benchmark_labels":{"belief_update":{"gauge-1":{"condition":"normal"}},"contradictions":[{"object_id":"gauge-1","attribute":"condition","values":["anomalous","normal"]}],"next_action":{"action_type":"verify","target_object":"gauge-1","preferred_agent_type":null},"explanation_evidence":["obs-1","obs-2"]},"evaluation":{"schema_version":"1.0","protocol_status":"draft","annotation_source":"normative_model","annotation_status":"derived","reference_generator_version":"evaluation-v1.0-generator.2","action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"evidence":{"provenance":{"obs-1":"edge-ai-1","obs-2":"iot-sensor-1","obs-distractor":"edge-ai-1"},"event_times":{"obs-1":"2026-02-19T12:00:10+00:00","obs-2":"2026-02-19T12:00:20+00:00","obs-distractor":"2026-02-19T12:00:13+00:00"},"arrival_times":{"obs-1":"2026-02-19T12:00:10+00:00","obs-2":"2026-02-19T12:00:39+00:00","obs-distractor":"2026-02-19T12:00:13+00:00"},"source_reliability":{"robot-1":0.825,"iot-sensor-1":0.942,"edge-ai-1":0.63},"confidence":{"obs-1":0.87686,"obs-2":0.87686,"obs-distractor":0.69},"state_epochs":{"obs-1":1,"obs-2":1,"obs-distractor":1},"supersedes_evidence_ids":{}},"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-049-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6773835982627716,"event_time":"2026-02-19T12:00:20+00:00","arrival_time":"2026-02-19T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7374218,"normal":0.2625782},"reference_distribution":{"anomalous":0.32261640173722833,"normal":0.6773835982627716}}],"belief_trajectory":[{"step_index":0,"new_evidence_ids":[],"available_evidence_ids":[],"active_evidence_ids":[],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["initial"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"undetermined","reference_state_status":"tied","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":[],"contradicting_evidence":[],"provenance":null,"reference_confidence":0.5,"event_time":null,"arrival_time":null,"source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.5,"normal":0.5}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":null,"resolution_status":"none","superseded_evidence_ids":[]}],"action":null,"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":true,"event_time":null,"arrival_time":null},{"step_index":1,"new_evidence_ids":["obs-1"],"available_evidence_ids":["obs-1"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"undetermined","prior_state_status":"tied","expected_change_direction":"changed","probability_direction":"strengthened","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7374218,"event_time":"2026-02-19T12:00:10+00:00","arrival_time":"2026-02-19T12:00:10+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.5,"normal":0.5},"reference_distribution":{"anomalous":0.7374218,"normal":0.2625782}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-19T12:00:10+00:00","arrival_time":"2026-02-19T12:00:10+00:00"},{"step_index":2,"new_evidence_ids":["obs-distractor"],"available_evidence_ids":["obs-1","obs-distractor"],"active_evidence_ids":["obs-1"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["isolate"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"anomalous","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"unchanged","probability_direction":"preserved","supporting_evidence":["obs-1"],"contradicting_evidence":[],"provenance":"edge-ai-1","reference_confidence":0.7374218,"event_time":"2026-02-19T12:00:13+00:00","arrival_time":"2026-02-19T12:00:13+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7374218,"normal":0.2625782},"reference_distribution":{"anomalous":0.7374218,"normal":0.2625782}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-049-condition-conflict","contradiction_present":false,"contradiction_type":null,"affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[],"involved_evidence_ids":[],"severity":null,"temporal_interpretation":"no_active_conflict","resolution_status":"none","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"inspect","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1"],"acceptable_supporting_evidence":["obs-1"],"acceptable_counterevidence":[],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"none","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":false,"should_affect_target":false,"event_time":"2026-02-19T12:00:13+00:00","arrival_time":"2026-02-19T12:00:13+00:00"},{"step_index":3,"new_evidence_ids":["obs-2"],"available_evidence_ids":["obs-1","obs-distractor","obs-2"],"active_evidence_ids":["obs-1","obs-2"],"stale_evidence_ids":[],"superseded_evidence_ids":[],"event_types":["delayed_evidence","contradiction_onset","update"],"reference_beliefs":[{"entity_id":"gauge-1","attribute":"condition","reference_state":"normal","reference_state_status":"unique","prior_state":"anomalous","prior_state_status":"unique","expected_change_direction":"changed","probability_direction":"reversed","supporting_evidence":["obs-2"],"contradicting_evidence":["obs-1"],"provenance":"iot-sensor-1","reference_confidence":0.6773835982627716,"event_time":"2026-02-19T12:00:20+00:00","arrival_time":"2026-02-19T12:00:39+00:00","source_reliability":null,"prior_distribution":{"anomalous":0.7374218,"normal":0.2625782},"reference_distribution":{"anomalous":0.32261640173722833,"normal":0.6773835982627716}}],"contradictions":[{"contradiction_id":"evaluation-v1-source_reliability-20260725-049-condition-conflict","contradiction_present":true,"contradiction_type":"same_epoch_value_conflict","affected_entity":"gauge-1","affected_attribute":"condition","valid_conflicting_evidence_pairs":[["obs-1","obs-2"]],"involved_evidence_ids":["obs-1","obs-2"],"severity":null,"temporal_interpretation":"same_state_epoch","resolution_status":"active","superseded_evidence_ids":[]}],"action":{"reference_action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"preferred_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"admissible_actions":[{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"inadmissible_actions":[{"action_type":"ignore","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"unsafe_actions":[{"action_type":"shutdown","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},{"action_type":"actuate","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}}],"action_utilities":null,"evidence_requirements":[{"action":{"action_type":"verify","target_entity_id":"gauge-1","agent_id":null,"required_agent_type":null,"parameters":{}},"required_supporting_evidence":["obs-1","obs-2"],"acceptable_supporting_evidence":["obs-1","obs-2"],"acceptable_counterevidence":["obs-1"],"rationale_requirements":null}],"rules":[{"rule_id":"evaluation-v1-action-policy","rule_type":"operational_policy","description":"Verify active contradictions, request observations for tied targets, inspect anomalous targets, and monitor normal targets.","affected_action_types":["verify","request_observation","inspect","monitor"],"affected_predicates":["condition"],"severity":null,"priority":null,"parameters":null},{"rule_id":"evaluation-v1-no-unverified-actuation","rule_type":"hard_constraint","description":"Do not actuate or shut down from benchmark evidence alone.","affected_action_types":["shutdown","actuate"],"affected_predicates":[],"severity":1.0,"priority":null,"parameters":null}],"allow_unsafe_reference":false},"contradiction_resolution_status":"active","required_relation_triples":[],"required_relation_paths":[],"target_entity_id":"gauge-1","target_attribute":"condition","expected_update":true,"should_affect_target":true,"event_time":"2026-02-19T12:00:20+00:00","arrival_time":"2026-02-19T12:00:39+00:00"}]},"metadata":{"generator":"creg.trajectory_generator.generate_trajectory_scenario","generator_version":"evaluation-v1.0-generator.2","normative_specification_sha256":"c1917910281e3fdbf5d6432181e68e3724dd5916e8e290f2f435d6ff11198b32","reference_model":"controlled-binary-bayes-v1","state_space":["anomalous","normal"],"prior_distribution":{"anomalous":0.5,"normal":0.5},"trajectory_regime":"source_reliability","case_index":49,"suite_seed":20260725,"counterfactual_pair_id":null,"confidence_semantics":"0.5 + (confidence - 0.5) * source_reliability","temporal_semantics":{"epoch_field":"state_epoch","same_epoch_opposing_claims":"contradict","older_epoch_arriving_late":"stale","delayed_current_epoch":"applicable","supersession_field":"supersedes_evidence_ids","correction_supersession":"remove_superseded_claim_from_active_set"},"relation_transfer_semantics":{"predicate":"measures","source_predicate":"reading","target_predicate":"condition","direction":"sensor_to_measured_entity","minimum_relation_confidence":1.0},"target_entity_id":"gauge-1","target_attribute":"condition","semantic_fingerprint":"ac50aa971c9ef8bd799d10af3d0fa59d74da2724ba813e1701c7784b670a5e2e"}}
